LaunchDarkly MCP
Vendor MCP136 toolsOAuth 2.1/DCRDeveloper ToolsMonitoringAutomationConnect to LaunchDarkly's hosted MCP server to manage feature flags, experiments, and release controls directly from your AI workflows.
LaunchDarkly MCP connector
-
Install the SDK
Section titled “Install the SDK”Terminal window npm install @scalekit-sdk/nodeTerminal window pip install scalekit -
Set your credentials
Section titled “Set your credentials”Add your Scalekit credentials to your
.envfile. Find values in app.scalekit.com > Developers > API Credentials..env SCALEKIT_ENVIRONMENT_URL=<your-environment-url>SCALEKIT_CLIENT_ID=<your-client-id>SCALEKIT_CLIENT_SECRET=<your-client-secret> -
Authorize and make your first call
Section titled “Authorize and make your first call”quickstart.ts import { ScalekitClient } from '@scalekit-sdk/node'import 'dotenv/config'const scalekit = new ScalekitClient(process.env.SCALEKIT_ENV_URL,process.env.SCALEKIT_CLIENT_ID,process.env.SCALEKIT_CLIENT_SECRET,)const actions = scalekit.actionsconst connector = 'launchdarklymcp'const identifier = 'user_123'// Generate an authorization link for the userconst { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })console.log('Authorize LaunchDarkly MCP:', link)process.stdout.write('Press Enter after authorizing...')await new Promise(r => process.stdin.once('data', r))// Make your first callconst result = await actions.executeTool({connector,identifier,toolName: 'launchdarklymcp_find_members',toolInput: {},})console.log(result)quickstart.py import osfrom scalekit.client import ScalekitClientfrom dotenv import load_dotenvload_dotenv()scalekit_client = ScalekitClient(env_url=os.getenv("SCALEKIT_ENV_URL"),client_id=os.getenv("SCALEKIT_CLIENT_ID"),client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),)actions = scalekit_client.actionsconnection_name = "launchdarklymcp"identifier = "user_123"# Generate an authorization link for the userlink_response = actions.get_authorization_link(connection_name=connection_name,identifier=identifier,)print("Authorize LaunchDarkly MCP:", link_response.link)input("Press Enter after authorizing...")# Make your first callresult = actions.execute_tool(tool_input={},tool_name="launchdarklymcp_find_members",connection_name=connection_name,identifier=identifier,)print(result)
What you can do
Section titled “What you can do”Connect this agent connector to let your agent:
- Update segment targets, segment rules, alert — Add or remove individual context keys from a segment’s included or excluded lists
- Alert toggle — Enable or disable an observability alert without changing its configuration
- Config toggle agentcontrol, setup agentcontrol, setup ai — Turn an AgentControl Config’s targeting on or off in a specific environment
- Search docs, contexts — Search LaunchDarkly documentation to retrieve authoritative reference material for flags, targeting rules, experiments, segments, AgentControl configs, SDKs, API fields, rollouts, metrics, and more
- Policies match release — Resolve which release policies would govern a flag in a given environment — a read-only dry-run of the server-side policy matching logic
- List segments, projects, alerts — List segments in a project environment
Tool list
Section titled “Tool list”Use the exact tool names from the Tool list below when you call execute_tool. If you’re not sure which name to use, list the tools available for the current user first.
launchdarklymcp_apply_approval_request#Apply an already-approved approval request. This executes the changes that were approved by reviewers. Only works on requests with reviewStatus 'approved'. Does NOT approve requests: that must be done by a human reviewer.3 params
Apply an already-approved approval request. This executes the changes that were approved by reviewers. Only works on requests with reviewStatus 'approved'. Does NOT approve requests: that must be done by a human reviewer.
idstringrequiredId for this operation.projectKeystringrequiredProject Key for this operation.commentstringoptionalComment for this operation.launchdarklymcp_archive_flag#Archive a feature flag (reversible). This is a soft-delete that can be undone. Recommended as the first step before permanent deletion. Always run check-removal-readiness before archiving.3 params
Archive a feature flag (reversible). This is a soft-delete that can be undone. Recommended as the first step before permanent deletion. Always run check-removal-readiness before archiving.
flagKeystringrequiredFlag Key for this operation.projectKeystringrequiredProject Key for this operation.commentstringoptionalComment for this operation.launchdarklymcp_check_removal_readiness#Check whether a feature flag is ready to be permanently removed from code. Analyzes SDK evaluations to confirm the flag is no longer in use.3 params
Check whether a feature flag is ready to be permanently removed from code. Analyzes SDK evaluations to confirm the flag is no longer in use.
envstringrequiredThe environment key to check flag removal readiness in.flagKeystringrequiredThe key of the feature flag to check for removal readiness.projectKeystringrequiredThe project key where the flag resides.launchdarklymcp_clone_agentcontrol_config_variation#Clone an existing AgentControl Config variation with selective overrides. Reads the source variation, applies any provided overrides (model, instructions, messages, parameters, tools), and creates a new variation. Returns both the source and created variation so you can compare the diff. Use this for A/B experimentation: change one thing at a time while keeping everything else constant.11 params
Clone an existing AgentControl Config variation with selective overrides. Reads the source variation, applies any provided overrides (model, instructions, messages, parameters, tools), and creates a new variation. Returns both the source and created variation so you can compare the diff. Use this for A/B experimentation: change one thing at a time while keeping everything else constant.
configKeystringrequiredConfig Key for this operation.keystringrequiredKey for this operation.namestringrequiredName for this operation.projectKeystringrequiredProject Key for this operation.sourceVariationKeystringrequiredSource Variation Key for this operation.instructionsstringoptionalInstructions for this operation.messagesarrayoptionalMessages for this operation.modelConfigKeystringoptionalModel Config Key for this operation.modelNamestringoptionalModel Name for this operation.parametersobjectoptionalParameters for this operation.toolsarrayoptionalTools for this operation.launchdarklymcp_clone_ai_config_variation#Clone an existing AI Config variation to create a new variation with the same settings.4 params
Clone an existing AI Config variation to create a new variation with the same settings.
configKeystringrequiredThe key of the AI Config that contains the variation to clone.projectKeystringrequiredThe project key identifying which project contains the AI Config.variationIdstringrequiredThe ID of the variation to clone.namestringoptionalThe name for the new cloned variation.launchdarklymcp_copy_flag_config#Copy a flag's targeting configuration from one environment to another. Common use: promote from staging to production. Optionally select which aspects to copy: targeting, rules, offVariation, prerequisites, on state. If the target environment requires approval, the response includes requiresApproval: true and an approvalUrl; follow the approvalUrl to submit the copy request for review.6 params
Copy a flag's targeting configuration from one environment to another. Common use: promote from staging to production. Optionally select which aspects to copy: targeting, rules, offVariation, prerequisites, on state. If the target environment requires approval, the response includes requiresApproval: true and an approvalUrl; follow the approvalUrl to submit the copy request for review.
flagKeystringrequiredFlag Key for this operation.projectKeystringrequiredProject Key for this operation.sourceEnvstringrequiredSource Env for this operation.targetEnvstringrequiredTarget Env for this operation.excludedActionsarrayoptionalExcluded Actions for this operation.includedActionsarrayoptionalIncluded Actions for this operation.launchdarklymcp_create_agent_graph#Create a new agent graph in a project. An agent graph defines a directed graph of AgentControl Configs for multi-agent workflows. Provide a rootConfigKey and edges to define the graph structure, or create the graph with just metadata and add edges later via update-agent-graph. If rootConfigKey or edges are provided, both must be present.6 params
Create a new agent graph in a project. An agent graph defines a directed graph of AgentControl Configs for multi-agent workflows. Provide a rootConfigKey and edges to define the graph structure, or create the graph with just metadata and add edges later via update-agent-graph. If rootConfigKey or edges are provided, both must be present.
keystringrequiredKey for this operation.namestringrequiredName for this operation.projectKeystringrequiredProject Key for this operation.descriptionstringoptionalDescription for this operation.edgesarrayoptionalEdges for this operation.rootConfigKeystringoptionalRoot Config Key for this operation.launchdarklymcp_create_agentcontrol_config#Create a new AgentControl Config in a project. This creates the config shell: use create-agentcontrol-config-variation next to add a model, prompts, and parameters. Mode determines whether variations use 'instructions' (agent), 'messages' (completion), or 'messages' (judge). Judge-mode configs evaluate other AgentControl Config outputs. IMPORTANT: evaluationMetricKey (format: $ld:ai:judge:<suffix>) is REQUIRED when mode is 'judge'; omitting it will cause a 400 error. For agent and completion mode it is not accepted. Pass viewKeys to link the new config to one or more views at creation time (Views are an Enterprise feature).8 params
Create a new AgentControl Config in a project. This creates the config shell: use create-agentcontrol-config-variation next to add a model, prompts, and parameters. Mode determines whether variations use 'instructions' (agent), 'messages' (completion), or 'messages' (judge). Judge-mode configs evaluate other AgentControl Config outputs. IMPORTANT: evaluationMetricKey (format: $ld:ai:judge:<suffix>) is REQUIRED when mode is 'judge'; omitting it will cause a 400 error. For agent and completion mode it is not accepted. Pass viewKeys to link the new config to one or more views at creation time (Views are an Enterprise feature).
keystringrequiredKey for this operation.modestringrequiredMode for this operation.namestringrequiredName for this operation.projectKeystringrequiredProject Key for this operation.descriptionstringoptionalDescription for this operation.evaluationMetricKeystringoptionalEvaluation Metric Key for this operation.tagsarrayoptionalTags for this operation.viewKeysarrayoptionalView Keys for this operation.launchdarklymcp_create_agentcontrol_config_variation#Create a variation for an AgentControl Config. A variation defines the model, prompts, parameters, and tools. modelConfigKey must be in Provider.model-id format (e.g. OpenAI.gpt-4o, Anthropic.claude-sonnet-4-5) for models to display correctly in the UI. Agent-mode configs use 'instructions' (a string); completion-mode configs use 'messages' (an array of {role, content} objects). To attach AI tools, pass the 'tools' array with {key, version} entries (create tools first with create-ai-tool). To attach judges, pass judgeConfiguration with a judges array of {judgeConfigKey, samplingRate} entries.11 params
Create a variation for an AgentControl Config. A variation defines the model, prompts, parameters, and tools. modelConfigKey must be in Provider.model-id format (e.g. OpenAI.gpt-4o, Anthropic.claude-sonnet-4-5) for models to display correctly in the UI. Agent-mode configs use 'instructions' (a string); completion-mode configs use 'messages' (an array of {role, content} objects). To attach AI tools, pass the 'tools' array with {key, version} entries (create tools first with create-ai-tool). To attach judges, pass judgeConfiguration with a judges array of {judgeConfigKey, samplingRate} entries.
configKeystringrequiredConfig Key for this operation.keystringrequiredKey for this operation.modelConfigKeystringrequiredModel Config Key for this operation.modelNamestringrequiredModel Name for this operation.namestringrequiredName for this operation.projectKeystringrequiredProject Key for this operation.instructionsstringoptionalInstructions for this operation.judgeConfigurationobjectoptionalJudge Configuration for this operation.messagesarrayoptionalMessages for this operation.parametersobjectoptionalParameters for this operation.toolsarrayoptionalTools for this operation.launchdarklymcp_create_ai_config#Create a new AI Config in a project. An AI Config manages AI model configurations with feature flag-style targeting and experimentation.5 params
Create a new AI Config in a project. An AI Config manages AI model configurations with feature flag-style targeting and experimentation.
keystringrequiredA unique key for the AI Config.namestringrequiredA human-readable name for the AI Config.projectKeystringrequiredThe project key where the AI Config will be created.descriptionstringoptionalAn optional description for the AI Config.tagsarrayoptionalOptional list of tags to associate with the AI Config.launchdarklymcp_create_ai_config_variation#Create a new variation for an AI Config with specific model, prompt, and parameter settings.5 params
Create a new variation for an AI Config with specific model, prompt, and parameter settings.
configKeystringrequiredThe key of the AI Config to create a new variation for.namestringrequiredThe name for the new variation.projectKeystringrequiredThe project key identifying which project contains the AI Config.modelobjectoptionalModel settings for the new variation such as model name and parameters.promptarrayoptionalPrompt messages array for the new variation.launchdarklymcp_create_ai_tool#Create a new AI tool definition in a project. The schema should be a raw JSON Schema object with type, properties, and required fields (e.g. {"type": "object", "properties": {...}}). Do NOT use the OpenAI function calling wrapper format. After creation, attach the tool to a variation using update-agentcontrol-config-variation.4 params
Create a new AI tool definition in a project. The schema should be a raw JSON Schema object with type, properties, and required fields (e.g. {"type": "object", "properties": {...}}). Do NOT use the OpenAI function calling wrapper format. After creation, attach the tool to a variation using update-agentcontrol-config-variation.
descriptionstringrequiredDescription for this operation.keystringrequiredKey for this operation.projectKeystringrequiredProject Key for this operation.schemaobjectrequiredSchema for this operation.launchdarklymcp_create_alert#Create a new observability alert that fires when a metric crosses a threshold.19 params
Create a new observability alert that fires when a metric crosses a threshold.
functionTypestringrequiredAggregator to monitor - one of Count, CountDistinct, CountDistinctKey, Min, Avg, P50, P90, P95, P99, Max, SumnamestringrequiredName for the alert (e.g., "High API Error Rate")productTypestringrequiredData source - one of Logs, Traces, Errors, Sessions, Metrics, EventsprojectKeystringrequiredThe LaunchDarkly project key (e.g., "default").autoInvestigationEnabledbooleanoptionalwhen true, each firing starts an automatic AI investigation and posts the diagnosis to the alert's destinationsdestinationsarrayoptionalArray of notification destinations, each with:functionColumnstringoptionalField to aggregate. Omit for Count; field name for others (e.g., "duration" for P90 latency)groupByarrayoptionalArray of dimension keys to alert per-group (e.g., ["service_name"] fires separately per service)investigationCooldownSecondsnumberoptionalminimum gap between automatic investigations. Keep at or above thresholdCooldown so a chatty alert doesn't re-investigate the same conditioninvestigationPermissionModestringoptional"read" investigates and reports; "read-write" additionally lets the investigation open a PRinvestigationPromptstringoptionalextra standing instructions prepended to each investigationinvestigationRepositoriesarrayoptionalrepos the investigation may read. Without these it cannot correlate a firing against a recent deploymessageContentstringoptionalCustom text included in alert notificationsquerystringoptionalFilter query string using search syntax (e.g., "service_name=api level=error")thresholdConditionstringoptional"Above", "Below", or "Outside" (Anomaly only)thresholdCooldownnumberoptionalSeconds to wait before re-notifying while still alertingthresholdTypestringoptional"Constant" compares against thresholdValue; "Anomaly" detects deviations automaticallythresholdValuenumberoptionalThe threshold to compare against. Required for Constant threshold alerts.thresholdWindownumberoptionalEvaluation window in seconds (e.g., 300 = look at the last 5 minutes)launchdarklymcp_create_approval_request#Create an approval request for a flag change in an environment that requires approvals. Provide the same semantic patch instructions you would use for a direct change. The request will be reviewed by approvers before taking effect. Does NOT approve the request: that must be done by a human reviewer.8 params
Create an approval request for a flag change in an environment that requires approvals. Provide the same semantic patch instructions you would use for a direct change. The request will be reviewed by approvers before taking effect. Does NOT approve the request: that must be done by a human reviewer.
descriptionstringrequiredDescription for this operation.envstringrequiredEnv for this operation.flagKeystringrequiredFlag Key for this operation.instructionsarrayrequiredInstructions for this operation.projectKeystringrequiredProject Key for this operation.commentstringoptionalComment for this operation.notifyMemberIdsarrayoptionalNotify Member Ids for this operation.notifyTeamKeysarrayoptionalNotify Team Keys for this operation.launchdarklymcp_create_automated_rollout_config#Record an automated rollout config in LaunchDarkly for a feature-flagged change.8 params
Record an automated rollout config in LaunchDarkly for a feature-flagged change.
environmentsarrayrequiredPer-environment rollout plan. Array of { environmentKey, releaseType?, override? } objects. `override` is { releaseMethod, rolloutContextKindKey?, stages?, metricKeys?, metricGroupKeys?, rollbackOnRegression? }.flagKeystringrequiredKey of the guarding feature flag (must already exist).projectKeystringrequiredLaunchDarkly project key (e.g., "default").endingVariationIdstringoptionalFor a multi-variate flag, the id of the variation the flag rolls out to. If omitted, a boolean flag assumes the true variation. A multi-variate flag requires both startingVariationId and endingVariationId to be set.prNumbernumberoptionalPR number.prUrlstringoptionalFull PR URL.repoFullNamestringoptionalGitHub repo as "owner/repo".startingVariationIdstringoptionalFor a multi-variate flag, the id of the variation the flag rolls out from. If omitted, a boolean flag assumes the false variation.launchdarklymcp_create_flag#Create a new feature flag in a project. Defaults to a boolean temporary flag. After creation the flag is OFF in all environments: use toggle-flag to enable it.13 params
Create a new feature flag in a project. Defaults to a boolean temporary flag. After creation the flag is OFF in all environments: use toggle-flag to enable it.
keystringrequiredKey for this operation.namestringrequiredName for this operation.projectKeystringrequiredProject Key for this operation.clientSideAvailabilityobjectoptionalClient Side Availability for this operation.customPropertiesobjectoptionalCustom Properties for this operation.descriptionstringoptionalDescription for this operation.kindstringoptionalKind for this operation.maintainerIdstringoptionalMaintainer Id for this operation.maintainerTeamKeystringoptionalMaintainer Team Key for this operation.tagsarrayoptionalTags for this operation.temporarybooleanoptionalTemporary for this operation.variationsarrayoptionalVariations for this operation.viewKeysarrayoptionalView Keys for this operation.launchdarklymcp_create_playground#Create a new LLM playground. A playground lets you compare AgentControl Config variations side-by-side. Provide a name and variants — each variant references an evaluation definition (by evaluationId) and a display position.3 params
Create a new LLM playground. A playground lets you compare AgentControl Config variations side-by-side. Provide a name and variants — each variant references an evaluation definition (by evaluationId) and a display position.
namestringrequiredName for this operation.projectKeystringrequiredProject Key for this operation.variantsarrayrequiredVariants for this operation.launchdarklymcp_create_prompt_snippet#Create a new reusable prompt snippet.6 params
Create a new reusable prompt snippet.
keystringrequiredA unique key for the prompt snippet.namestringrequiredThe name of the prompt snippet.projectKeystringrequiredThe project key.textstringrequiredThe text content of the prompt snippet.descriptionstringoptionalA description of the prompt snippet.tagsarrayoptionalArray of tags to categorize the prompt snippet.launchdarklymcp_create_segment#Create a new segment in a project environment. The segment is empty after creation — use update-segment-rules to add targeting rules or update-segment-targets to add individual context keys. Segment keys are immutable after creation: choose carefully. Pass viewKeys to link the new segment to one or more views at creation time (Views are an Enterprise feature).8 params
Create a new segment in a project environment. The segment is empty after creation — use update-segment-rules to add targeting rules or update-segment-targets to add individual context keys. Segment keys are immutable after creation: choose carefully. Pass viewKeys to link the new segment to one or more views at creation time (Views are an Enterprise feature).
environmentKeystringrequiredEnvironment Key for this operation.keystringrequiredKey for this operation.namestringrequiredName for this operation.projectKeystringrequiredProject Key for this operation.descriptionstringoptionalDescription for this operation.tagsarrayoptionalTags for this operation.unboundedbooleanoptionalUnbounded for this operation.viewKeysarrayoptionalView Keys for this operation.launchdarklymcp_createdashboard#Create a new empty dashboard (visualization) for organizing charts.3 params
Create a new empty dashboard (visualization) for organizing charts.
namestringrequiredName for the dashboard (e.g., "Frontend Errors Overview")projectKeystringrequiredThe LaunchDarkly project key (e.g., "default").timePresetstringoptionalDefault time range. Use format like "last_24_hours", "last_7_days", "last_30_days"launchdarklymcp_createdataset#Create a new offline dataset for AI evaluation. Provide a dataset name, filename, and format (csv, json, or jsonl). The dataset is created in pending status and must be uploaded separately. Returns the dataset ID and upload URL.6 params
Create a new offline dataset for AI evaluation. Provide a dataset name, filename, and format (csv, json, or jsonl). The dataset is created in pending status and must be uploaded separately. Returns the dataset ID and upload URL.
filenamestringrequiredFilename for this operation.formatstringrequiredFormat for this operation.namestringrequiredName for this operation.projectKeystringrequiredProject Key for this operation.checksumstringoptionalChecksum for this operation.sizenumberoptionalSize for this operation.launchdarklymcp_createevaluation#Create a new AI evaluation definition. An evaluation defines a comparison between AI Config variations using a dataset and judge criteria. After creation, use run-evaluation to start an evaluation run.5 params
Create a new AI evaluation definition. An evaluation defines a comparison between AI Config variations using a dataset and judge criteria. After creation, use run-evaluation to start an evaluation run.
namestringrequiredA human-readable name for the evaluation.projectKeystringrequiredThe project key identifying which project to create the evaluation in.configKeystringoptionalThe key of the AI Config to evaluate.datasetIdstringoptionalThe ID of the offline dataset to use for this evaluation.variationKeysarrayoptionalArray of variation keys from the AI Config to include in the evaluation.launchdarklymcp_createexperiment#Create a new experiment on a flag or AgentControl Config. An experiment measures the impact of different variations on specified metrics. You must provide the initial iteration definition including a hypothesis, metrics, treatments, and flag configuration. One treatment must be marked as the baseline. Use `methodology` to pick the results-analysis approach (`bayesian` default, `frequentist`, or `export_only` for data-export-only mode). Use `analysisConfig` to set thresholds and multiple-comparison correction. Use `iteration.attributes` to declare slicing dimensions and `iteration.covariateId` to enable stratified sampling.12 params
Create a new experiment on a flag or AgentControl Config. An experiment measures the impact of different variations on specified metrics. You must provide the initial iteration definition including a hypothesis, metrics, treatments, and flag configuration. One treatment must be marked as the baseline. Use `methodology` to pick the results-analysis approach (`bayesian` default, `frequentist`, or `export_only` for data-export-only mode). Use `analysisConfig` to set thresholds and multiple-comparison correction. Use `iteration.attributes` to declare slicing dimensions and `iteration.covariateId` to enable stratified sampling.
environmentKeystringrequiredEnvironment Key for this operation.iterationobjectrequiredIteration for this operation.keystringrequiredKey for this operation.namestringrequiredName for this operation.projectKeystringrequiredProject Key for this operation.analysisConfigobjectoptionalAnalysis Config for this operation.dataSourcestringoptionalData Source for this operation.descriptionstringoptionalDescription for this operation.holdoutIdstringoptionalHoldout Id for this operation.maintainerIdstringoptionalMaintainer Id for this operation.methodologystringoptionalMethodology for this operation.tagsarrayoptionalTags for this operation.launchdarklymcp_creategraph#Add a chart/graph to an existing dashboard.14 params
Add a chart/graph to an existing dashboard.
dashboardIdnumberrequiredID of the dashboard to add the graph toexpressionsarrayrequiredArray of aggregations, each with:productTypestringrequiredData source - one of:projectKeystringrequiredThe LaunchDarkly project key (e.g., "default").titlestringrequiredChart title (e.g., "Error Rate by Service")typestringrequiredChart type - one of:bucketBystringoptionalField to bucket by for time-seriesbucketCountnumberoptionalNumber of time bucketsdisplaystringoptionalDisplay style - "Line", "Stacked", "Stacked area"groupByarrayoptionalArray of dimension keys to group bygroupByLimitnumberoptionalMaximum number of series to render when groupBy is set. High-cardinality dimensions (URLs, click selectors, account IDs) can produce hundreds of series and make the dashboard UI unresponsive — keep this small. Ignored when groupBy is empty.limitAggregatorstringoptionalWhich aggregator to rank groups by when applying groupByLimit. Use the same aggregator you ranked by in query-aggregations.limitColumnstringoptionalColumn used alongside limitAggregator when ranking groups (e.g. "duration" for P90 latency ranking). Ignored for Count.querystringoptionalFilter query string using search syntaxlaunchdarklymcp_createmetric#Create a new metric in a LaunchDarkly project.14 params
Create a new metric in a LaunchDarkly project.
keystringrequiredKey for this operation.measureTypestringrequiredMeasure Type for this operation.namestringrequiredName for this operation.projectKeystringrequiredProject Key for this operation.successCriteriastringrequiredSuccess Criteria for this operation.descriptionstringoptionalDescription for this operation.eventKeystringoptionalEvent Key for this operation.kindstringoptionalKind for this operation.randomizationUnitsarrayoptionalRandomization Units for this operation.selectorstringoptionalSelector for this operation.tagsarrayoptionalTags for this operation.unitstringoptionalUnit for this operation.urlsarrayoptionalUrls for this operation.valueAggregationstringoptionalValue Aggregation for this operation.launchdarklymcp_createproject#Create a new LaunchDarkly project. Projects are top-level containers for feature flags and environments.3 params
Create a new LaunchDarkly project. Projects are top-level containers for feature flags and environments.
keystringrequiredA unique key for the new project. Used in API calls and SDK configuration.namestringrequiredA human-readable name for the project.tagsarrayoptionalOptional list of tags to categorize the project.launchdarklymcp_delete_agentcontrol_config#Permanently delete an AgentControl Config. THIS IS IRREVERSIBLE. Requires confirm=true to execute. Prefer archiving (update-agentcontrol-config with archived: true) when possible.3 params
Permanently delete an AgentControl Config. THIS IS IRREVERSIBLE. Requires confirm=true to execute. Prefer archiving (update-agentcontrol-config with archived: true) when possible.
configKeystringrequiredConfig Key for this operation.confirmbooleanrequiredConfirm for this operation.projectKeystringrequiredProject Key for this operation.launchdarklymcp_delete_agentcontrol_config_variation#Permanently delete an AgentControl Config variation. THIS IS IRREVERSIBLE. Requires confirm=true to execute.4 params
Permanently delete an AgentControl Config variation. THIS IS IRREVERSIBLE. Requires confirm=true to execute.
configKeystringrequiredConfig Key for this operation.confirmbooleanrequiredConfirm for this operation.projectKeystringrequiredProject Key for this operation.variationKeystringrequiredVariation Key for this operation.launchdarklymcp_delete_ai_config#Permanently delete an AI Config and all its variations. This is irreversible.2 params
Permanently delete an AI Config and all its variations. This is irreversible.
configKeystringrequiredThe key of the AI Config to permanently delete.projectKeystringrequiredThe project key identifying which project contains the AI Config to delete.launchdarklymcp_delete_ai_config_variation#Delete a variation from an AI Config. This is permanent and cannot be undone.3 params
Delete a variation from an AI Config. This is permanent and cannot be undone.
configKeystringrequiredThe key of the AI Config that contains the variation to delete.projectKeystringrequiredThe project key identifying which project contains the AI Config.variationIdstringrequiredThe ID of the variation to permanently delete.launchdarklymcp_delete_ai_tool#Permanently delete an AI tool definition. THIS IS IRREVERSIBLE. Any AgentControl Config variations referencing this tool will lose the attachment. Requires confirm=true to execute.3 params
Permanently delete an AI tool definition. THIS IS IRREVERSIBLE. Any AgentControl Config variations referencing this tool will lose the attachment. Requires confirm=true to execute.
confirmbooleanrequiredConfirm for this operation.projectKeystringrequiredProject Key for this operation.toolKeystringrequiredTool Key for this operation.launchdarklymcp_delete_alert#Permanently delete an observability alert. THIS IS IRREVERSIBLE. Requires confirm=true to execute. Use get-alert first to verify you are deleting the right alert.3 params
Permanently delete an observability alert. THIS IS IRREVERSIBLE. Requires confirm=true to execute. Use get-alert first to verify you are deleting the right alert.
alertIdnumberrequiredThe numeric ID of the alert to deleteconfirmbooleanrequiredMust be true to execute the deletionprojectKeystringrequiredThe LaunchDarkly project key (e.g., "default").launchdarklymcp_delete_dashboard#Permanently delete a dashboard (visualization) and all of its graphs. THIS IS IRREVERSIBLE. Requires confirm=true to execute. Use get-dashboard first to verify you are deleting the right dashboard.3 params
Permanently delete a dashboard (visualization) and all of its graphs. THIS IS IRREVERSIBLE. Requires confirm=true to execute. Use get-dashboard first to verify you are deleting the right dashboard.
confirmbooleanrequiredMust be true to execute the deletiondashboardIdnumberrequiredThe numeric ID of the dashboard to delete (from list-dashboards)projectKeystringrequiredThe LaunchDarkly project key (e.g., "default").launchdarklymcp_delete_flag#Permanently delete a feature flag and all its targeting rules across all environments. This is irreversible.3 params
Permanently delete a feature flag and all its targeting rules across all environments. This is irreversible.
confirmbooleanrequiredMust be set to true to confirm permanent deletion of the flag.flagKeystringrequiredThe key of the feature flag to permanently delete.projectKeystringrequiredThe project key where the flag resides.launchdarklymcp_delete_prompt_snippet#Permanently delete a prompt snippet. THIS IS IRREVERSIBLE. Any AgentControl Config variations referencing this snippet will lose their reference. Requires confirm=true to execute.3 params
Permanently delete a prompt snippet. THIS IS IRREVERSIBLE. Any AgentControl Config variations referencing this snippet will lose their reference. Requires confirm=true to execute.
confirmbooleanrequiredConfirm for this operation.projectKeystringrequiredProject Key for this operation.snippetKeystringrequiredSnippet Key for this operation.launchdarklymcp_deleteagentgraph#Permanently delete an agent graph and all of its edges. THIS IS IRREVERSIBLE. Requires confirm=true to execute.3 params
Permanently delete an agent graph and all of its edges. THIS IS IRREVERSIBLE. Requires confirm=true to execute.
confirmbooleanrequiredConfirm for this operation.graphKeystringrequiredGraph Key for this operation.projectKeystringrequiredProject Key for this operation.launchdarklymcp_deletedataset#Permanently delete an offline dataset and its associated metadata. THIS IS IRREVERSIBLE. Requires confirm=true to execute.3 params
Permanently delete an offline dataset and its associated metadata. THIS IS IRREVERSIBLE. Requires confirm=true to execute.
confirmbooleanrequiredMust be set to true to confirm the irreversible deletion of the dataset.datasetIdstringrequiredThe unique identifier of the dataset to permanently delete.projectKeystringrequiredThe project key identifying which project the dataset belongs to.launchdarklymcp_find_members#Search for LaunchDarkly account members and return their IDs. Supports flexible matching:3 params
Search for LaunchDarkly account members and return their IDs. Supports flexible matching:
emailsarrayoptionalEmails for this operation.limitnumberoptionalLimit for this operation.querystringoptionalQuery for this operation.launchdarklymcp_find_stale_flags#Find feature flags that are candidates for cleanup. Returns a prioritized list of stale flags sorted by staleness (worst first). Categories: inactive_30d (no requests in period), launched_no_changes (fully rolled out, no recent changes), never_requested (created but never evaluated). Defaults to showing temporary flags inactive for 30+ days.10 params
Find feature flags that are candidates for cleanup. Returns a prioritized list of stale flags sorted by staleness (worst first). Categories: inactive_30d (no requests in period), launched_no_changes (fully rolled out, no recent changes), never_requested (created but never evaluated). Defaults to showing temporary flags inactive for 30+ days.
projectKeystringrequiredProject Key for this operation.envstringoptionalEnv for this operation.evalWindownumberoptionalEval Window for this operation.inactiveDaysnumberoptionalInactive Days for this operation.includeEvalCountsbooleanoptionalInclude Eval Counts for this operation.includeOnlystringoptionalInclude Only for this operation.maintainerIdstringoptionalMaintainer Id for this operation.maintainerTeamKeystringoptionalMaintainer Team Key for this operation.useCriticalEnvsbooleanoptionalUse Critical Envs for this operation.viewstringoptionalView for this operation.launchdarklymcp_get_agent_graph#Get a specific agent graph by key, including its full edge structure. Each edge connects a source AgentControl Config to a target AgentControl Config with optional handoff data.2 params
Get a specific agent graph by key, including its full edge structure. Each edge connects a source AgentControl Config to a target AgentControl Config with optional handoff data.
graphKeystringrequiredGraph Key for this operation.projectKeystringrequiredProject Key for this operation.launchdarklymcp_get_agentcontrol_config#Get detailed configuration for a single AgentControl Config including all its variations. Each variation includes its model, instructions or messages, parameters, attached tools, and judgeConfiguration (attached judges with judgeConfigKey and samplingRate). For judge-mode configs the response also includes evaluationMetricKey.2 params
Get detailed configuration for a single AgentControl Config including all its variations. Each variation includes its model, instructions or messages, parameters, attached tools, and judgeConfiguration (attached judges with judgeConfigKey and samplingRate). For judge-mode configs the response also includes evaluationMetricKey.
configKeystringrequiredConfig Key for this operation.projectKeystringrequiredProject Key for this operation.launchdarklymcp_get_agentcontrol_config_health#Health check for an AgentControl Config. Detects common issues: missing models (NO MODEL in UI), missing prompts, orphaned tool references, and empty configs with no variations. Returns a health verdict (healthy, warning, unhealthy) with specific issues and per-variation summaries. Run before updating or experimenting with a config.2 params
Health check for an AgentControl Config. Detects common issues: missing models (NO MODEL in UI), missing prompts, orphaned tool references, and empty configs with no variations. Returns a health verdict (healthy, warning, unhealthy) with specific issues and per-variation summaries. Run before updating or experimenting with a config.
configKeystringrequiredConfig Key for this operation.projectKeystringrequiredProject Key for this operation.launchdarklymcp_get_agentcontrol_config_targeting#Read the targeting configuration for an AgentControl Config in a specific environment. Returns variations (with their _id UUIDs and names), individual targets, custom rules, fallthrough (default rule), and off variation. The variation name returned here can be passed as 'variationKey' to update-agentcontrol-config-targeting, update-agentcontrol-config-rollout, and update-agentcontrol-config-targets. Alternatively, use get-agentcontrol-config to obtain the variation's slug key.3 params
Read the targeting configuration for an AgentControl Config in a specific environment. Returns variations (with their _id UUIDs and names), individual targets, custom rules, fallthrough (default rule), and off variation. The variation name returned here can be passed as 'variationKey' to update-agentcontrol-config-targeting, update-agentcontrol-config-rollout, and update-agentcontrol-config-targets. Alternatively, use get-agentcontrol-config to obtain the variation's slug key.
configKeystringrequiredConfig Key for this operation.envstringrequiredEnv for this operation.projectKeystringrequiredProject Key for this operation.launchdarklymcp_get_ai_config#Get details about a specific AI Config including its variations and metadata.2 params
Get details about a specific AI Config including its variations and metadata.
configKeystringrequiredThe key of the AI Config to retrieve.projectKeystringrequiredThe project key where the AI Config resides.launchdarklymcp_get_ai_config_health#Get the health status of an AI Config including latency, error rates, and evaluation metrics.3 params
Get the health status of an AI Config including latency, error rates, and evaluation metrics.
configKeystringrequiredThe key of the AI Config to retrieve health status for.environmentKeystringrequiredThe environment key to retrieve health metrics from.projectKeystringrequiredThe project key identifying which project contains the AI Config.launchdarklymcp_get_ai_config_status_across_envs#Get the status of an AI Config across all environments in a project.2 params
Get the status of an AI Config across all environments in a project.
configKeystringrequiredThe key of the AI Config to retrieve status across all environments.projectKeystringrequiredThe project key identifying which project contains the AI Config.launchdarklymcp_get_ai_config_targeting#Get the targeting rules and rollout configuration for an AI Config in a specific environment.3 params
Get the targeting rules and rollout configuration for an AI Config in a specific environment.
configKeystringrequiredThe key of the AI Config to retrieve targeting rules for.envstringrequiredThe environment key to retrieve targeting configuration from.projectKeystringrequiredThe project key identifying which project contains the AI Config.launchdarklymcp_get_ai_tool#Get a single AI tool definition including its full schema. Use to inspect a tool's parameters before attaching it to an AgentControl Config variation.2 params
Get a single AI tool definition including its full schema. Use to inspect a tool's parameters before attaching it to an AgentControl Config variation.
projectKeystringrequiredProject Key for this operation.toolKeystringrequiredTool Key for this operation.launchdarklymcp_get_alert#Get detailed information about a specific observability alert.2 params
Get detailed information about a specific observability alert.
alertIdnumberrequiredThe numeric ID of the alert (from list-alerts)projectKeystringrequiredThe LaunchDarkly project key (e.g., "default").launchdarklymcp_get_context_instances#Get all stored instances of a specific context by kind and key. Returns every recorded occurrence of the context, including its full attribute set (e.g., merchantCountryCode, disbursementRail) and which SDK/application reported each instance.6 params
Get all stored instances of a specific context by kind and key. Returns every recorded occurrence of the context, including its full attribute set (e.g., merchantCountryCode, disbursementRail) and which SDK/application reported each instance.
environmentKeystringrequiredEnvironment Key for this operation.keystringrequiredKey for this operation.kindstringrequiredKind for this operation.projectKeystringrequiredProject Key for this operation.continuationTokenstringoptionalContinuation Token for this operation.limitnumberoptionalLimit for this operation.launchdarklymcp_get_doc#Fetch the full markdown content of a LaunchDarkly documentation page.1 param
Fetch the full markdown content of a LaunchDarkly documentation page.
urlstringrequiredUrl for this operation.launchdarklymcp_get_flag#Get full details about a specific feature flag including all variations, targeting rules across environments, and metadata.3 params
Get full details about a specific feature flag including all variations, targeting rules across environments, and metadata.
flagKeystringrequiredThe feature flag key to retrieve full details for.projectKeystringrequiredThe project key identifying which project contains the flag.envstringoptionalOptional environment key to scope the flag details to a specific environment.launchdarklymcp_get_flag_health#Get health indicators for a feature flag including evaluation counts, error rates, and usage patterns.3 params
Get health indicators for a feature flag including evaluation counts, error rates, and usage patterns.
envstringrequiredThe environment key to check flag health in.flagKeystringrequiredThe feature flag key to retrieve health indicators for.projectKeystringrequiredThe project key identifying which project contains the flag.launchdarklymcp_get_flag_status_across_envs#Get the on/off status and targeting summary for a feature flag across all environments in a project.2 params
Get the on/off status and targeting summary for a feature flag across all environments in a project.
flagKeystringrequiredThe feature flag key to get status for across all environments.projectKeystringrequiredThe project key identifying which project contains the flag.launchdarklymcp_get_member_self#Get the profile of the currently authenticated member, including their role and permissions.0 params
Get the profile of the currently authenticated member, including their role and permissions.
launchdarklymcp_get_playground#Get details about a specific LLM playground, including its variants (evaluation definitions and their positions).2 params
Get details about a specific LLM playground, including its variants (evaluation definitions and their positions).
playgroundIdstringrequiredPlayground Id for this operation.projectKeystringrequiredProject Key for this operation.launchdarklymcp_get_prompt_snippet#Get a specific prompt snippet by key. Returns the snippet's name, text content, tags, version, and creation time.2 params
Get a specific prompt snippet by key. Returns the snippet's name, text content, tags, version, and creation time.
projectKeystringrequiredProject Key for this operation.snippetKeystringrequiredSnippet Key for this operation.launchdarklymcp_get_segment#Get detailed configuration for a single segment in an environment. Returns rules, included targets, excluded targets, tags, and creation date. Use to verify segment state after creation or updates.3 params
Get detailed configuration for a single segment in an environment. Returns rules, included targets, excluded targets, tags, and creation date. Use to verify segment state after creation or updates.
environmentKeystringrequiredEnvironment Key for this operation.projectKeystringrequiredProject Key for this operation.segmentKeystringrequiredSegment Key for this operation.launchdarklymcp_get_service_connections_usage#Get a time series of service connection minutes from your LaunchDarkly account. Use this for capacity planning, cost analysis, and before/after deploy comparisons (e.g. compare daily incremental minutes around a deploy date).12 params
Get a time series of service connection minutes from your LaunchDarkly account. Use this for capacity planning, cost analysis, and before/after deploy comparisons (e.g. compare daily incremental minutes around a deploy date).
aggregationTypestringoptionalAggregation Type for this operation.connectionTypearrayoptionalConnection Type for this operation.environmentKeyarrayoptionalEnvironment Key for this operation.fromstringoptionalFrom for this operation.granularitystringoptionalGranularity for this operation.groupByarrayoptionalGroup By for this operation.projectKeyarrayoptionalProject Key for this operation.relayVersionarrayoptionalRelay Version for this operation.sdkNamearrayoptionalSdk Name for this operation.sdkTypearrayoptionalSdk Type for this operation.sdkVersionarrayoptionalSdk Version for this operation.tostringoptionalTo for this operation.launchdarklymcp_getdashboard#Get detailed information about a specific dashboard including all its graphs.2 params
Get detailed information about a specific dashboard including all its graphs.
dashboardIdnumberrequiredThe numeric ID of the dashboardprojectKeystringrequiredThe LaunchDarkly project key (e.g., "default").launchdarklymcp_getdataset#Get details about a specific offline dataset by ID, including its processing status and row count.2 params
Get details about a specific offline dataset by ID, including its processing status and row count.
datasetIdstringrequiredThe unique identifier of the dataset to retrieve.projectKeystringrequiredThe project key identifying which project the dataset belongs to.launchdarklymcp_getenvironment#Get details about a specific environment in a project, including its keys and settings.2 params
Get details about a specific environment in a project, including its keys and settings.
environmentKeystringrequiredThe key of the environment to retrieve.projectKeystringrequiredThe key of the project that contains the environment.launchdarklymcp_getevaluation#Get details about a specific evaluation definition, including its configuration and last run status.2 params
Get details about a specific evaluation definition, including its configuration and last run status.
evaluationIdstringrequiredThe unique identifier of the evaluation definition to retrieve.projectKeystringrequiredThe project key identifying which project the evaluation belongs to.launchdarklymcp_getevaluationrunsummary#Get the summary results of a completed evaluation run, including pass/fail counts and aggregate scores.3 params
Get the summary results of a completed evaluation run, including pass/fail counts and aggregate scores.
evaluationIdstringrequiredThe unique identifier of the evaluation definition.projectKeystringrequiredThe project key identifying which project the evaluation belongs to.runIdstringrequiredThe unique identifier of the evaluation run to retrieve the summary for.launchdarklymcp_getexperiment#Get details about a specific experiment including its configuration, current iteration status, and metric assignments.3 params
Get details about a specific experiment including its configuration, current iteration status, and metric assignments.
environmentKeystringrequiredThe environment key where the experiment exists.experimentKeystringrequiredThe experiment key identifying the experiment to retrieve.projectKeystringrequiredThe project key identifying the project containing the experiment.launchdarklymcp_getexperimentmetricresults#Get detailed statistical results for a single metric on an experiment iteration. Returns, per treatment: sample sizes (analyzedUnitCount, trafficCount, conversionCount), the observed mean and standard deviation, and a `statistics` block with the lift versus control (relativeDifferences: estimate plus lower/upper interval bounds and, for frequentist experiments, a per-comparison pValue), the overall pValue, Bayesian probabilities (probabilityToBeBest, probabilityToBeatBaseline, expectedLoss), and an isSignificant flag. Reads from LaunchDarkly's internal analysis API. Defaults to the current iteration and the latest analysis; pass iterationId to target a previous iteration. Use disableMultipleComparisonCorrection / disableSequentialTesting to see uncorrected numbers. Use get-experiment-results for a cross-metric overview, or get-experiment to discover metric keys.7 params
Get detailed statistical results for a single metric on an experiment iteration. Returns, per treatment: sample sizes (analyzedUnitCount, trafficCount, conversionCount), the observed mean and standard deviation, and a `statistics` block with the lift versus control (relativeDifferences: estimate plus lower/upper interval bounds and, for frequentist experiments, a per-comparison pValue), the overall pValue, Bayesian probabilities (probabilityToBeBest, probabilityToBeatBaseline, expectedLoss), and an isSignificant flag. Reads from LaunchDarkly's internal analysis API. Defaults to the current iteration and the latest analysis; pass iterationId to target a previous iteration. Use disableMultipleComparisonCorrection / disableSequentialTesting to see uncorrected numbers. Use get-experiment-results for a cross-metric overview, or get-experiment to discover metric keys.
environmentKeystringrequiredEnvironment Key for this operation.experimentKeystringrequiredExperiment Key for this operation.metricKeystringrequiredMetric Key for this operation.projectKeystringrequiredProject Key for this operation.disableMultipleComparisonCorrectionbooleanoptionalDisable Multiple Comparison Correction for this operation.disableSequentialTestingbooleanoptionalDisable Sequential Testing for this operation.iterationIdstringoptionalIteration Id for this operation.launchdarklymcp_getexperimentresults#Get an overall results summary for an experiment, across every metric on the current iteration. Discovers the iteration's metrics, then fetches each metric's analysis from LaunchDarkly's internal results API and returns a compact per-metric summary: which treatment is leading (isBest) — the arm with the highest probability to beat the baseline for Bayesian experiments, or the lowest p-value versus control for frequentist (note: not significance-gated, so a treatment can be flagged leading even when nothing is significant) — each treatment's lift versus control, whether it's statistically significant, and sample sizes. Pass iterationId to summarize a previous iteration. For the full per-treatment statistics (intervals, p-values, Bayesian probabilities) on one metric, use get-experiment-metric-results.6 params
Get an overall results summary for an experiment, across every metric on the current iteration. Discovers the iteration's metrics, then fetches each metric's analysis from LaunchDarkly's internal results API and returns a compact per-metric summary: which treatment is leading (isBest) — the arm with the highest probability to beat the baseline for Bayesian experiments, or the lowest p-value versus control for frequentist (note: not significance-gated, so a treatment can be flagged leading even when nothing is significant) — each treatment's lift versus control, whether it's statistically significant, and sample sizes. Pass iterationId to summarize a previous iteration. For the full per-treatment statistics (intervals, p-values, Bayesian probabilities) on one metric, use get-experiment-metric-results.
environmentKeystringrequiredEnvironment Key for this operation.experimentKeystringrequiredExperiment Key for this operation.projectKeystringrequiredProject Key for this operation.disableMultipleComparisonCorrectionbooleanoptionalDisable Multiple Comparison Correction for this operation.disableSequentialTestingbooleanoptionalDisable Sequential Testing for this operation.iterationIdstringoptionalIteration Id for this operation.launchdarklymcp_getkeys#Discover available data keys/dimensions for a product type.6 params
Discover available data keys/dimensions for a product type.
productTypestringrequiredOne of "logs", "traces", "sessions", "errors", "metrics", "events"projectKeystringrequiredThe LaunchDarkly project key (e.g., "default").startDatestringrequiredISO format start date (e.g., "2024-01-15T10:00:00Z")endDatestringoptionalISO format end date (defaults to current time)limitnumberoptionalMaximum number of keys to returnsearchstringoptionalFilter keys by namelaunchdarklymcp_getmetric#Get details about a specific metric including its configuration and associated experiments.2 params
Get details about a specific metric including its configuration and associated experiments.
metricKeystringrequiredThe key of the metric to retrieve.projectKeystringrequiredThe key of the project that contains the metric.launchdarklymcp_getproject#Get details about a specific LaunchDarkly project, including its environments and settings.1 param
Get details about a specific LaunchDarkly project, including its environments and settings.
projectKeystringrequiredThe key of the project to retrieve.launchdarklymcp_getsdkactive#Check whether any SDKs have been active in a given environment. Returns true if any SDK has initialized or sent events in the environment. Use this to verify that an environment is actually in use before cleanup. Optionally filter by sdkName or sdkWrapperName to check a specific SDK.4 params
Check whether any SDKs have been active in a given environment. Returns true if any SDK has initialized or sent events in the environment. Use this to verify that an environment is actually in use before cleanup. Optionally filter by sdkName or sdkWrapperName to check a specific SDK.
environmentKeystringrequiredEnvironment Key for this operation.projectKeystringrequiredProject Key for this operation.sdkNamestringoptionalSdk Name for this operation.sdkWrapperNamestringoptionalSdk Wrapper Name for this operation.launchdarklymcp_invite_members#Invite one or more people to the LaunchDarkly account by email. Each invitee receives an email invitation to join. Optionally assign a role (reader, writer, admin) — defaults to reader if not specified.2 params
Invite one or more people to the LaunchDarkly account by email. Each invitee receives an email invitation to join. Optionally assign a role (reader, writer, admin) — defaults to reader if not specified.
emailsarrayrequiredEmails for this operation.rolestringoptionalRole for this operation.launchdarklymcp_list_agent_graphs#List all agent graph definitions in a project.3 params
List all agent graph definitions in a project.
projectKeystringrequiredThe project key for the LaunchDarkly project.limitnumberoptionalMaximum number of agent graphs to return per page.offsetnumberoptionalOffset for pagination.launchdarklymcp_list_agentcontrol_configs#Search and browse AgentControl Configs in a project. Returns a paginated list with key, name, mode (agent, completion, or judge), tags, variation count, and a `usedInGraphs` array listing the agent graph keys that reference each config (as the graph root or as an edge source/target). An empty `usedInGraphs` means the config is not referenced by any graph (orphaned). If graph usage cannot be loaded, `usedInGraphs` is omitted entirely (rather than empty) so an absent field is never mistaken for orphaned. Use query to search by name or key, tags to filter by tag, or view to only include configs linked to a view (Views are an Enterprise feature).7 params
Search and browse AgentControl Configs in a project. Returns a paginated list with key, name, mode (agent, completion, or judge), tags, variation count, and a `usedInGraphs` array listing the agent graph keys that reference each config (as the graph root or as an edge source/target). An empty `usedInGraphs` means the config is not referenced by any graph (orphaned). If graph usage cannot be loaded, `usedInGraphs` is omitted entirely (rather than empty) so an absent field is never mistaken for orphaned. Use query to search by name or key, tags to filter by tag, or view to only include configs linked to a view (Views are an Enterprise feature).
projectKeystringrequiredProject Key for this operation.limitnumberoptionalLimit for this operation.offsetnumberoptionalOffset for this operation.querystringoptionalQuery for this operation.sortstringoptionalSort for this operation.tagsarrayoptionalTags for this operation.viewstringoptionalView for this operation.launchdarklymcp_list_ai_configs#List all AI Configs in a project with their current status and variation count.4 params
List all AI Configs in a project with their current status and variation count.
projectKeystringrequiredThe project key to list AI Configs from.limitnumberoptionalMaximum number of AI Configs to return per page.offsetnumberoptionalOffset for pagination.querystringoptionalSearch query to filter AI Configs by name or key.launchdarklymcp_list_ai_tools#List AI tool definitions in a project. Returns each tool's key, description, and schema. Tools are attached to AgentControl Config variations to give models function-calling capabilities.2 params
List AI tool definitions in a project. Returns each tool's key, description, and schema. Tools are attached to AgentControl Config variations to give models function-calling capabilities.
projectKeystringrequiredProject Key for this operation.limitnumberoptionalLimit for this operation.launchdarklymcp_list_alerts#List existing observability alerts for the project.2 params
List existing observability alerts for the project.
projectKeystringrequiredThe LaunchDarkly project key (e.g., "default").searchstringoptionalFilter alerts by name (case-insensitive substring match)launchdarklymcp_list_approval_requests#List pending approval requests for a flag in an environment. Shows status, review state, and who requested the change. Use to check on approval progress after creating a request.3 params
List pending approval requests for a flag in an environment. Shows status, review state, and who requested the change. Use to check on approval progress after creating a request.
envstringrequiredEnv for this operation.flagKeystringrequiredFlag Key for this operation.projectKeystringrequiredProject Key for this operation.launchdarklymcp_list_playgrounds#List LLM playgrounds in a project. Returns playground names, variant counts, and timestamps. Supports search by name and pagination.5 params
List LLM playgrounds in a project. Returns playground names, variant counts, and timestamps. Supports search by name and pagination.
projectKeystringrequiredProject Key for this operation.limitnumberoptionalLimit for this operation.offsetnumberoptionalOffset for this operation.searchstringoptionalSearch for this operation.statusstringoptionalStatus for this operation.launchdarklymcp_list_projects#List LaunchDarkly projects in the account. Use to discover project keys before calling project-scoped tools. Filtering: use `query` to search by project name or key (case-insensitive), `tags` to filter by tag (all must match). Sorting: use `sort` with `name` or `-name`. Pagination: responses include `totalCount` and `pageInfo.offset`. To get the next page, set `offset` to the current offset + limit.5 params
List LaunchDarkly projects in the account. Use to discover project keys before calling project-scoped tools. Filtering: use `query` to search by project name or key (case-insensitive), `tags` to filter by tag (all must match). Sorting: use `sort` with `name` or `-name`. Pagination: responses include `totalCount` and `pageInfo.offset`. To get the next page, set `offset` to the current offset + limit.
limitnumberoptionalLimit for this operation.offsetnumberoptionalOffset for this operation.querystringoptionalQuery for this operation.sortstringoptionalSort for this operation.tagsarrayoptionalTags for this operation.launchdarklymcp_list_prompt_snippets#List prompt snippets in a project. Prompt snippets are reusable text blocks that can be referenced inside AgentControl Config variation prompts to keep common instructions consistent. Returns key, name, text, version, and tags.4 params
List prompt snippets in a project. Prompt snippets are reusable text blocks that can be referenced inside AgentControl Config variation prompts to keep common instructions consistent. Returns key, name, text, version, and tags.
projectKeystringrequiredProject Key for this operation.filterstringoptionalFilter for this operation.limitnumberoptionalLimit for this operation.offsetnumberoptionalOffset for this operation.launchdarklymcp_list_segments#List segments in a project environment. Returns a paginated list with rule counts and target counts. Use query to search by name or key, tags to filter by tag, or view to only include segments linked to a view (Views are an Enterprise feature). Always list first to avoid creating duplicates.8 params
List segments in a project environment. Returns a paginated list with rule counts and target counts. Use query to search by name or key, tags to filter by tag, or view to only include segments linked to a view (Views are an Enterprise feature). Always list first to avoid creating duplicates.
environmentKeystringrequiredEnvironment Key for this operation.projectKeystringrequiredProject Key for this operation.limitnumberoptionalLimit for this operation.offsetnumberoptionalOffset for this operation.querystringoptionalQuery for this operation.sortstringoptionalSort for this operation.tagsarrayoptionalTags for this operation.viewstringoptionalView for this operation.launchdarklymcp_listdashboards#List existing dashboards (visualizations) for the project.3 params
List existing dashboards (visualizations) for the project.
projectKeystringrequiredThe LaunchDarkly project key (e.g., "default").limitnumberoptionalMaximum number of dashboards to returnsearchstringoptionalFilter dashboards by namelaunchdarklymcp_listdatasets#List offline datasets for a project. Returns id, name, status, row count, and creation info for each dataset.3 params
List offline datasets for a project. Returns id, name, status, row count, and creation info for each dataset.
projectKeystringrequiredThe project key identifying which project to list datasets for.limitnumberoptionalMaximum number of datasets to return per page.offsetnumberoptionalOffset for pagination. Set to current offset + limit to get the next page.launchdarklymcp_listevaluations#List AI Config evaluations in a project. Returns evaluation definitions with their names, associated config keys, and last run info.4 params
List AI Config evaluations in a project. Returns evaluation definitions with their names, associated config keys, and last run info.
projectKeystringrequiredThe project key identifying which project to list evaluations for.limitnumberoptionalMaximum number of evaluations to return per page.offsetnumberoptionalOffset for pagination. Set to current offset + limit to get the next page.searchstringoptionalSearch term to filter evaluations by name.launchdarklymcp_listexperiments#List experiments in a project, optionally filtered by environment. Returns key, name, description, and current iteration status for each experiment.6 params
List experiments in a project, optionally filtered by environment. Returns key, name, description, and current iteration status for each experiment.
projectKeystringrequiredProject Key for this operation.environmentKeystringoptionalEnvironment Key for this operation.flagKeystringoptionalFlag Key for this operation.limitnumberoptionalLimit for this operation.offsetnumberoptionalOffset for this operation.statusstringoptionalStatus for this operation.launchdarklymcp_listflags#Search and browse feature flags in a project. Returns a paginated list scoped to a single environment.13 params
Search and browse feature flags in a project. Returns a paginated list scoped to a single environment.
projectKeystringrequiredProject Key for this operation.envstringoptionalEnv for this operation.limitnumberoptionalLimit for this operation.maintainerIdstringoptionalMaintainer Id for this operation.maintainerTeamKeystringoptionalMaintainer Team Key for this operation.offsetnumberoptionalOffset for this operation.querystringoptionalQuery for this operation.sdkAvailabilitystringoptionalSdk Availability for this operation.sortstringoptionalSort for this operation.statestringoptionalState for this operation.tagsarrayoptionalTags for this operation.typestringoptionalType for this operation.viewstringoptionalView for this operation.launchdarklymcp_listmetricevents#List recent event keys received by a LaunchDarkly project — used to check which events are actively flowing before creating a metric. Returns up to 50 event keys with last-seen timestamps. If the event key you need isn't here, it may not be instrumented yet.3 params
List recent event keys received by a LaunchDarkly project — used to check which events are actively flowing before creating a metric. Returns up to 50 event keys with last-seen timestamps. If the event key you need isn't here, it may not be instrumented yet.
projectKeystringrequiredProject Key for this operation.environmentKeystringoptionalEnvironment Key for this operation.querystringoptionalQuery for this operation.launchdarklymcp_listmetrics#List metrics in a LaunchDarkly project. Returns key, name, measureType (count/occurrence/value), eventKey, successCriteria, tags, and how many flags each metric is attached to.13 params
List metrics in a LaunchDarkly project. Returns key, name, measureType (count/occurrence/value), eventKey, successCriteria, tags, and how many flags each metric is attached to.
projectKeystringrequiredProject Key for this operation.dataSourceKeysarrayoptionalData Source Keys for this operation.eventKindstringoptionalEvent Kind for this operation.hasConnectionsbooleanoptionalHas Connections for this operation.isNumericbooleanoptionalIs Numeric for this operation.limitnumberoptionalLimit for this operation.maintainerIdsarrayoptionalMaintainer Ids for this operation.maintainerTeamKeystringoptionalMaintainer Team Key for this operation.metricUsedInstringoptionalMetric Used In for this operation.offsetnumberoptionalOffset for this operation.querystringoptionalQuery for this operation.sortstringoptionalSort for this operation.tagsarrayoptionalTags for this operation.launchdarklymcp_listreleasepolicies#List release policies for a project. Each policy defines preferred release methods and the metrics or metric groups that automatically attach to guarded rollouts when the policy's conditions match (e.g. specific environments or flag tags).1 param
List release policies for a project. Each policy defines preferred release methods and the metrics or metric groups that automatically attach to guarded rollouts when the policy's conditions match (e.g. specific environments or flag tags).
projectKeystringrequiredProject Key for this operation.launchdarklymcp_manage_expiring_targets#List, add, update, or remove expiring targets on a flag. Expiring targets are automatically removed from targeting after a specified date. Dates are shown as ISO strings with days-until-expiry computed. Variation IDs are resolved to human-readable names.8 params
List, add, update, or remove expiring targets on a flag. Expiring targets are automatically removed from targeting after a specified date. Dates are shown as ISO strings with days-until-expiry computed. Variation IDs are resolved to human-readable names.
actionstringrequiredAction for this operation.envstringrequiredEnv for this operation.flagKeystringrequiredFlag Key for this operation.projectKeystringrequiredProject Key for this operation.contextKeystringoptionalContext Key for this operation.contextKindstringoptionalContext Kind for this operation.expiresAtstringoptionalExpires At for this operation.variationIdstringoptionalVariation Id for this operation.launchdarklymcp_match_release_policies#Resolve which release policies would govern a flag in a given environment — a read-only dry-run of the server-side policy matching logic. Does not create or modify anything.4 params
Resolve which release policies would govern a flag in a given environment — a read-only dry-run of the server-side policy matching logic. Does not create or modify anything.
environmentKeystringrequiredEnvironment Key for this operation.projectKeystringrequiredProject Key for this operation.flagKeystringoptionalFlag Key for this operation.flagTagsarrayoptionalFlag Tags for this operation.launchdarklymcp_previewgraph#Preview a chart/graph inline WITHOUT saving it to a dashboard.
Always use this tool first when a user asks to create or visualize a chart.
Returns both the graph configuration and the queried metrics data so the user can see the chart rendered inline. After showing the preview, ask the user if they want to save it to a dashboard (using create-graph).11 params
Preview a chart/graph inline WITHOUT saving it to a dashboard. Always use this tool first when a user asks to create or visualize a chart. Returns both the graph configuration and the queried metrics data so the user can see the chart rendered inline. After showing the preview, ask the user if they want to save it to a dashboard (using create-graph).
expressionsarrayrequiredExpressions for this operation.productTypestringrequiredProduct Type for this operation.projectKeystringrequiredProject Key for this operation.titlestringrequiredTitle for this operation.typestringrequiredType for this operation.bucketCountnumberoptionalBucket Count for this operation.displaystringoptionalDisplay for this operation.endDatestringoptionalEnd Date for this operation.groupByarrayoptionalGroup By for this operation.querystringoptionalQuery for this operation.startDatestringoptionalStart Date for this operation.launchdarklymcp_query_change_history#Query the audit log to find what changed in a LaunchDarkly account.9 params
Query the audit log to find what changed in a LaunchDarkly account.
endDatestringoptionalEnd date for the audit log query (ISO 8601 format).envstringoptionalThe environment key to scope the query to.limitnumberoptionalMaximum number of audit log entries to return.projectKeystringoptionalThe project key to scope the audit log query to.querystringoptionalFree-text search query to filter audit log entries.resourceKeystringoptionalThe key of the specific resource to filter audit log entries for.resourceKindstringoptionalThe kind of resource to filter audit log entries for (e.g. flag, segment).startDatestringoptionalStart date for the audit log query (ISO 8601 format).tagsarrayoptionalArray of tags to filter audit log entries by.launchdarklymcp_queryaggregations#Retrieve bucketed, aggregated values over time for a product type.
Returns time-series buckets (not raw events) suitable for charting trends, comparing groups, and computing sums/averages/percentiles.
Use this instead of query-logs/query-traces/query-sessions/query-error-groups when you want aggregated values over a window rather than individual records.7 params
Retrieve bucketed, aggregated values over time for a product type. Returns time-series buckets (not raw events) suitable for charting trends, comparing groups, and computing sums/averages/percentiles. Use this instead of query-logs/query-traces/query-sessions/query-error-groups when you want aggregated values over a window rather than individual records.
productTypestringrequiredProduct Type for this operation.projectKeystringrequiredProject Key for this operation.startDatestringrequiredStart Date for this operation.endDatestringoptionalEnd Date for this operation.expressionsarrayoptionalExpressions for this operation.groupBystringoptionalGroup By for this operation.querystringoptionalQuery for this operation.launchdarklymcp_queryerrorgroups#Query project error groups.
Retrieve error groups for a given project with explicit date range parameters.6 params
Query project error groups. Retrieve error groups for a given project with explicit date range parameters.
projectKeystringrequiredProject Key for this operation.startDatestringrequiredStart Date for this operation.countnumberoptionalCount for this operation.endDatestringoptionalEnd Date for this operation.pagenumberoptionalPage for this operation.querystringoptionalQuery for this operation.launchdarklymcp_queryflagevaluations#Query flag evaluations for a session.
Retrieve flag evaluation events for a specific session to understand which feature flags were evaluated during that session.7 params
Query flag evaluations for a session. Retrieve flag evaluation events for a specific session to understand which feature flags were evaluated during that session.
projectKeystringrequiredProject Key for this operation.sessionSecureIdstringrequiredSession Secure Id for this operation.startDatestringrequiredStart Date for this operation.directionstringoptionalDirection for this operation.endDatestringoptionalEnd Date for this operation.limitnumberoptionalLimit for this operation.querystringoptionalQuery for this operation.launchdarklymcp_querylogs#Query project logs.
Retrieve logs for a given project with explicit date range parameters.6 params
Query project logs. Retrieve logs for a given project with explicit date range parameters.
projectKeystringrequiredProject Key for this operation.startDatestringrequiredStart Date for this operation.directionstringoptionalDirection for this operation.endDatestringoptionalEnd Date for this operation.limitnumberoptionalLimit for this operation.querystringoptionalQuery for this operation.launchdarklymcp_querysessions#Query project sessions.
Retrieve sessions for a given project with explicit date range parameters.8 params
Query project sessions. Retrieve sessions for a given project with explicit date range parameters.
projectKeystringrequiredProject Key for this operation.startDatestringrequiredStart Date for this operation.countnumberoptionalCount for this operation.endDatestringoptionalEnd Date for this operation.pagenumberoptionalPage for this operation.querystringoptionalQuery for this operation.sortDescbooleanoptionalSort Desc for this operation.sortFieldstringoptionalSort Field for this operation.launchdarklymcp_querytimelineevents#Query timeline indicator events for a session.
Retrieve timeline indicator events for a specific session to understand what happened during that session.
Keep in mind that this will not include flag evaluation events, you must use the query-flag-evaluations tool to retrieve those.2 params
Query timeline indicator events for a session. Retrieve timeline indicator events for a specific session to understand what happened during that session. Keep in mind that this will not include flag evaluation events, you must use the query-flag-evaluations tool to retrieve those.
projectKeystringrequiredProject Key for this operation.sessionSecureIdstringrequiredSession Secure Id for this operation.launchdarklymcp_querytraces#Query project traces.
Retrieve traces for a given project with explicit date range parameters.8 params
Query project traces. Retrieve traces for a given project with explicit date range parameters.
projectKeystringrequiredProject Key for this operation.startDatestringrequiredStart Date for this operation.directionstringoptionalDirection for this operation.endDatestringoptionalEnd Date for this operation.limitnumberoptionalLimit for this operation.querystringoptionalQuery for this operation.sortColumnstringoptionalSort Column for this operation.sortDirectionstringoptionalSort Direction for this operation.launchdarklymcp_runevaluation#Start a new run of an AI evaluation. This executes the evaluation against the configured dataset and judge criteria. Returns the run ID and status.2 params
Start a new run of an AI evaluation. This executes the evaluation against the configured dataset and judge criteria. Returns the run ID and status.
evaluationIdstringrequiredThe unique identifier of the evaluation to run.projectKeystringrequiredThe project key identifying which project the evaluation belongs to.launchdarklymcp_saveandstartexperimentiteration#Stop the current running iteration, create a new draft iteration with the provided field updates applied, and start it — the API-recommended way to mutate treatments, metrics, methodology, or other fields that are locked while an iteration is running. Provide `changeJustification` to record why a new iteration is needed. Field inputs are the same as `update-experiment`; updates are checked against the new iteration's not_started mutability rules. Fields not allowed in not_started are returned under `skipped` rather than being sent.23 params
Stop the current running iteration, create a new draft iteration with the provided field updates applied, and start it — the API-recommended way to mutate treatments, metrics, methodology, or other fields that are locked while an iteration is running. Provide `changeJustification` to record why a new iteration is needed. Field inputs are the same as `update-experiment`; updates are checked against the new iteration's not_started mutability rules. Fields not allowed in not_started are returned under `skipped` rather than being sent.
environmentKeystringrequiredEnvironment Key for this operation.experimentKeystringrequiredExperiment Key for this operation.projectKeystringrequiredProject Key for this operation.analysisConfigobjectoptionalAnalysis Config for this operation.attributesarrayoptionalAttributes for this operation.canReshuffleTrafficbooleanoptionalCan Reshuffle Traffic for this operation.changeJustificationstringoptionalChange Justification for this operation.covariateIdstringoptionalCovariate Id for this operation.dataSourcestringoptionalData Source for this operation.descriptionstringoptionalDescription for this operation.flagsobjectoptionalFlags for this operation.flagSettingsobjectoptionalFlag Settings for this operation.holdoutIdstringoptionalHoldout Id for this operation.hypothesisstringoptionalHypothesis for this operation.maintainerIdstringoptionalMaintainer Id for this operation.methodologystringoptionalMethodology for this operation.metricsarrayoptionalMetrics for this operation.namestringoptionalName for this operation.primaryFunnelKeystringoptionalPrimary Funnel Key for this operation.primarySingleMetricKeystringoptionalPrimary Single Metric Key for this operation.randomizationUnitstringoptionalRandomization Unit for this operation.tagsarrayoptionalTags for this operation.treatmentsarrayoptionalTreatments for this operation.launchdarklymcp_search_contexts#Search for stored LaunchDarkly contexts in an environment by kind, key, or attribute value. Returns context records including their stored attributes (e.g., merchantCountryCode, disbursementRail) and when the context was last seen.7 params
Search for stored LaunchDarkly contexts in an environment by kind, key, or attribute value. Returns context records including their stored attributes (e.g., merchantCountryCode, disbursementRail) and when the context was last seen.
environmentKeystringrequiredEnvironment Key for this operation.projectKeystringrequiredProject Key for this operation.continuationTokenstringoptionalContinuation Token for this operation.filterstringoptionalFilter for this operation.kindstringoptionalKind for this operation.limitnumberoptionalLimit for this operation.sortstringoptionalSort for this operation.launchdarklymcp_search_docs#Search LaunchDarkly documentation to retrieve authoritative reference material for flags, targeting rules, experiments, segments, AgentControl configs, SDKs, API fields, rollouts, metrics, and more.3 params
Search LaunchDarkly documentation to retrieve authoritative reference material for flags, targeting rules, experiments, segments, AgentControl configs, SDKs, API fields, rollouts, metrics, and more.
querystringrequiredQuery for this operation.limitnumberoptionalLimit for this operation.sectionstringoptionalSection for this operation.launchdarklymcp_setup_agentcontrol_config#Create an AgentControl Config with its first variation in one step. This is the recommended way to set up a new AgentControl Config: it creates the config, adds a variation with model and prompts, and verifies everything is configured correctly. Returns the full config detail with variation. To attach AI tools, pass the 'tools' array with {key, version} entries. IMPORTANT: evaluationMetricKey (format: $ld:ai:judge:<suffix>) is REQUIRED when mode is 'judge'. Pass viewKeys to link the new config to one or more views at creation time (Views are an Enterprise feature). Use create-agentcontrol-config + create-agentcontrol-config-variation separately only when you need more control.16 params
Create an AgentControl Config with its first variation in one step. This is the recommended way to set up a new AgentControl Config: it creates the config, adds a variation with model and prompts, and verifies everything is configured correctly. Returns the full config detail with variation. To attach AI tools, pass the 'tools' array with {key, version} entries. IMPORTANT: evaluationMetricKey (format: $ld:ai:judge:<suffix>) is REQUIRED when mode is 'judge'. Pass viewKeys to link the new config to one or more views at creation time (Views are an Enterprise feature). Use create-agentcontrol-config + create-agentcontrol-config-variation separately only when you need more control.
keystringrequiredKey for this operation.modestringrequiredMode for this operation.modelConfigKeystringrequiredModel Config Key for this operation.modelNamestringrequiredModel Name for this operation.namestringrequiredName for this operation.projectKeystringrequiredProject Key for this operation.variationKeystringrequiredVariation Key for this operation.variationNamestringrequiredVariation Name for this operation.descriptionstringoptionalDescription for this operation.evaluationMetricKeystringoptionalEvaluation Metric Key for this operation.instructionsstringoptionalInstructions for this operation.messagesarrayoptionalMessages for this operation.parametersobjectoptionalParameters for this operation.tagsarrayoptionalTags for this operation.toolsarrayoptionalTools for this operation.viewKeysarrayoptionalView Keys for this operation.launchdarklymcp_setup_ai_config#Initialize an AI Config with its first variation and targeting setup in one step.5 params
Initialize an AI Config with its first variation and targeting setup in one step.
configKeystringrequiredThe key of the AI Config to initialize.environmentKeystringrequiredThe environment key to set up the AI Config in.projectKeystringrequiredThe project key identifying which project to set up the AI Config in.modelobjectoptionalModel settings for the initial variation.promptarrayoptionalPrompt messages for the initial variation.launchdarklymcp_startexperimentiteration#Start an experiment iteration. This begins data collection for the experiment's current draft iteration and starts allocating live end-user traffic across its treatments. The experiment's flag must be toggled on, a randomization unit must be set, and at least one treatment must have a non-zero allocation percent.4 params
Start an experiment iteration. This begins data collection for the experiment's current draft iteration and starts allocating live end-user traffic across its treatments. The experiment's flag must be toggled on, a randomization unit must be set, and at least one treatment must have a non-zero allocation percent.
environmentKeystringrequiredEnvironment Key for this operation.experimentKeystringrequiredExperiment Key for this operation.projectKeystringrequiredProject Key for this operation.changeJustificationstringoptionalChange Justification for this operation.launchdarklymcp_startguardedrollout#Start a guarded rollout on a flag's default rule (fallthrough). A guarded rollout progressively increases traffic to the test variation through a series of stages while monitoring metrics for regressions. Each stage specifies a rolloutWeight (percentage in thousandths, e.g. 10000 = 10%) and a monitoring window in milliseconds. Metrics define what to monitor and whether to notify or rollback on regression. Requires the flag to be on and not already have an active guarded rollout. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-approval-request` with the returned instructions to submit it for review.11 params
Start a guarded rollout on a flag's default rule (fallthrough). A guarded rollout progressively increases traffic to the test variation through a series of stages while monitoring metrics for regressions. Each stage specifies a rolloutWeight (percentage in thousandths, e.g. 10000 = 10%) and a monitoring window in milliseconds. Metrics define what to monitor and whether to notify or rollback on regression. Requires the flag to be on and not already have an active guarded rollout. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-approval-request` with the returned instructions to submit it for review.
controlVariationIdstringrequiredControl Variation Id for this operation.environmentKeystringrequiredEnvironment Key for this operation.flagKeystringrequiredFlag Key for this operation.metricsarrayrequiredMetrics for this operation.projectKeystringrequiredProject Key for this operation.randomizationUnitstringrequiredRandomization Unit for this operation.stagesarrayrequiredStages for this operation.testVariationIdstringrequiredTest Variation Id for this operation.commentstringoptionalComment for this operation.metricSourcesarrayoptionalMetric Sources for this operation.updateDefaultRuleOnCompletionbooleanoptionalUpdate Default Rule On Completion for this operation.launchdarklymcp_stopexperimentiteration#Stop the currently running iteration of an experiment. Data collection ends and the iteration moves to the `stopped` status. A winning treatment is required to stop: pass `winningTreatmentId` (the `_id` of one of the iteration's treatments, available from get-experiment) and an optional `winningReason` explaining the call. If the experiment was inconclusive, declare the baseline/control treatment as the winner.5 params
Stop the currently running iteration of an experiment. Data collection ends and the iteration moves to the `stopped` status. A winning treatment is required to stop: pass `winningTreatmentId` (the `_id` of one of the iteration's treatments, available from get-experiment) and an optional `winningReason` explaining the call. If the experiment was inconclusive, declare the baseline/control treatment as the winner.
environmentKeystringrequiredEnvironment Key for this operation.experimentKeystringrequiredExperiment Key for this operation.projectKeystringrequiredProject Key for this operation.winningTreatmentIdstringrequiredWinning Treatment Id for this operation.winningReasonstringoptionalWinning Reason for this operation.launchdarklymcp_stopguardedrollout#Stop an active guarded rollout on a flag's default rule (fallthrough). This immediately halts the progressive rollout and locks the flag to its current state. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-approval-request` with the returned instructions to submit it for review.4 params
Stop an active guarded rollout on a flag's default rule (fallthrough). This immediately halts the progressive rollout and locks the flag to its current state. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-approval-request` with the returned instructions to submit it for review.
environmentKeystringrequiredEnvironment Key for this operation.flagKeystringrequiredFlag Key for this operation.projectKeystringrequiredProject Key for this operation.commentstringoptionalComment for this operation.launchdarklymcp_toggle_agentcontrol_config#Turn an AgentControl Config's targeting on or off in a specific environment. Returns the previous and new state. This is equivalent to 'turnFlagOn' / 'turnFlagOff' for feature flags. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-agentcontrol-config-approval` with the returned instructions to submit it for review.5 params
Turn an AgentControl Config's targeting on or off in a specific environment. Returns the previous and new state. This is equivalent to 'turnFlagOn' / 'turnFlagOff' for feature flags. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-agentcontrol-config-approval` with the returned instructions to submit it for review.
configKeystringrequiredConfig Key for this operation.envstringrequiredEnv for this operation.onbooleanrequiredOn for this operation.projectKeystringrequiredProject Key for this operation.commentstringoptionalComment for this operation.launchdarklymcp_toggle_alert#Enable or disable an observability alert without changing its configuration.3 params
Enable or disable an observability alert without changing its configuration.
alertIdnumberrequiredThe numeric ID of the alert (from list-alerts)enabledbooleanrequiredtrue to enable the alert, false to disable itprojectKeystringrequiredThe LaunchDarkly project key (e.g., "default").launchdarklymcp_toggle_flag#Turn a feature flag on or off in a specific environment. When off, all users receive the off variation.5 params
Turn a feature flag on or off in a specific environment. When off, all users receive the off variation.
envstringrequiredThe environment key where the flag should be toggled.flagKeystringrequiredThe feature flag key to toggle on or off.onbooleanrequiredSet to true to turn the flag on, or false to turn it off.projectKeystringrequiredThe project key identifying which project contains the flag.commentstringoptionalOptional comment describing why the flag was toggled.launchdarklymcp_update_agentcontrol_config#Update an AgentControl Config's metadata: name, description, tags, or archive status. Does NOT modify variations: use update-agentcontrol-config-variation for model, prompt, or parameter changes. Set archived: true to archive (reversible).6 params
Update an AgentControl Config's metadata: name, description, tags, or archive status. Does NOT modify variations: use update-agentcontrol-config-variation for model, prompt, or parameter changes. Set archived: true to archive (reversible).
configKeystringrequiredConfig Key for this operation.projectKeystringrequiredProject Key for this operation.archivedbooleanoptionalArchived for this operation.descriptionstringoptionalDescription for this operation.namestringoptionalName for this operation.tagsarrayoptionalTags for this operation.launchdarklymcp_update_agentcontrol_config_rollout#Update the default (fallthrough) rule for an AgentControl Config in an environment. Set a percentage rollout across variations, or serve a single variation to all unmatched contexts. Weights must sum to 100. Use human-friendly percentages (e.g., 80 for 80%). Accepts a variation key (from get-agentcontrol-config) or variation name (from get-agentcontrol-config-targeting); the tool resolves either to the internal variation _id (UUID) before patching. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-agentcontrol-config-approval` with the returned instructions to submit it for review.9 params
Update the default (fallthrough) rule for an AgentControl Config in an environment. Set a percentage rollout across variations, or serve a single variation to all unmatched contexts. Weights must sum to 100. Use human-friendly percentages (e.g., 80 for 80%). Accepts a variation key (from get-agentcontrol-config) or variation name (from get-agentcontrol-config-targeting); the tool resolves either to the internal variation _id (UUID) before patching. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-agentcontrol-config-approval` with the returned instructions to submit it for review.
configKeystringrequiredConfig Key for this operation.envstringrequiredEnv for this operation.projectKeystringrequiredProject Key for this operation.rolloutTypestringrequiredRollout Type for this operation.bucketBystringoptionalBucket By for this operation.commentstringoptionalComment for this operation.contextKindstringoptionalContext Kind for this operation.variationKeystringoptionalVariation Key for this operation.weightsarrayoptionalWeights for this operation.launchdarklymcp_update_agentcontrol_config_variation#Update an AgentControl Config variation's name, description, model, instructions/messages, parameters, attached tools, or judge configuration. All fields are optional: only provided fields are updated. Pass 'name' to rename the variation in place without recreating it (avoids changing the variation _id). To attach tools, pass the 'tools' array with {key, version} entries (create tools first with create-ai-tool). Pass an empty tools array to detach all tools. To attach judges, pass judgeConfiguration with a judges array of {judgeConfigKey, samplingRate} entries. Pass an empty judges array to detach all judges.12 params
Update an AgentControl Config variation's name, description, model, instructions/messages, parameters, attached tools, or judge configuration. All fields are optional: only provided fields are updated. Pass 'name' to rename the variation in place without recreating it (avoids changing the variation _id). To attach tools, pass the 'tools' array with {key, version} entries (create tools first with create-ai-tool). Pass an empty tools array to detach all tools. To attach judges, pass judgeConfiguration with a judges array of {judgeConfigKey, samplingRate} entries. Pass an empty judges array to detach all judges.
configKeystringrequiredConfig Key for this operation.projectKeystringrequiredProject Key for this operation.variationKeystringrequiredVariation Key for this operation.descriptionstringoptionalDescription for this operation.instructionsstringoptionalInstructions for this operation.judgeConfigurationobjectoptionalJudge Configuration for this operation.messagesarrayoptionalMessages for this operation.modelConfigKeystringoptionalModel Config Key for this operation.modelNamestringoptionalModel Name for this operation.namestringoptionalName for this operation.parametersobjectoptionalParameters for this operation.toolsarrayoptionalTools for this operation.launchdarklymcp_update_ai_config#Update the metadata for an AI Config such as name, description, and tags.5 params
Update the metadata for an AI Config such as name, description, and tags.
configKeystringrequiredThe key of the AI Config to update.projectKeystringrequiredThe project key identifying which project contains the AI Config.descriptionstringoptionalThe updated description for the AI Config.namestringoptionalThe updated display name for the AI Config.tagsarrayoptionalArray of tags to associate with the AI Config.launchdarklymcp_update_ai_config_individual_targets#Update the individual user targeting for an AI Config in a specific environment.4 params
Update the individual user targeting for an AI Config in a specific environment.
configKeystringrequiredThe key of the AI Config to update.envstringrequiredThe environment key where the AI Config targeting will be updated.projectKeystringrequiredThe project key for the LaunchDarkly project.targetsarrayoptionalThe individual user targets to set for this AI Config.launchdarklymcp_update_ai_config_rollout#Update the rollout percentages for an AI Config's default rule in a specific environment.4 params
Update the rollout percentages for an AI Config's default rule in a specific environment.
configKeystringrequiredThe key of the AI Config to update.envstringrequiredThe environment key where the rollout will be updated.projectKeystringrequiredThe project key for the LaunchDarkly project.rolloutobjectoptionalThe rollout configuration defining percentage splits across variations.launchdarklymcp_update_ai_config_targeting_rules#Update the targeting rules for an AI Config in a specific environment.4 params
Update the targeting rules for an AI Config in a specific environment.
configKeystringrequiredThe key of the AI Config to update targeting rules for.envstringrequiredThe environment key where targeting rules will be updated.projectKeystringrequiredThe project key identifying which project contains the AI Config.rulesarrayoptionalArray of targeting rule objects to apply to the AI Config.launchdarklymcp_update_ai_config_variation#Update a specific variation of an AI Config, including its prompt, model settings, and parameters.6 params
Update a specific variation of an AI Config, including its prompt, model settings, and parameters.
configKeystringrequiredThe key of the AI Config that contains the variation to update.projectKeystringrequiredThe project key identifying which project contains the AI Config.variationIdstringrequiredThe ID of the variation to update.modelobjectoptionalModel settings for this variation such as model name and parameters.namestringoptionalThe updated name for the variation.promptarrayoptionalPrompt messages array for this variation.launchdarklymcp_update_ai_tool#Update an AI tool definition's description or schema. All fields are optional: only provided fields are updated. The schema should be a raw JSON Schema object with type, properties, and required fields.4 params
Update an AI tool definition's description or schema. All fields are optional: only provided fields are updated. The schema should be a raw JSON Schema object with type, properties, and required fields.
projectKeystringrequiredProject Key for this operation.toolKeystringrequiredTool Key for this operation.descriptionstringoptionalDescription for this operation.schemaobjectoptionalSchema for this operation.launchdarklymcp_update_alert#Update an existing observability alert. Only the fields you provide are changed; everything else is preserved.20 params
Update an existing observability alert. Only the fields you provide are changed; everything else is preserved.
alertIdnumberrequiredThe numeric ID of the alert to update (from list-alerts)projectKeystringrequiredThe LaunchDarkly project key (e.g., "default").autoInvestigationEnabledbooleanoptionalwhen true, each firing starts an automatic AI investigation and posts the diagnosis to the alert's destinationsdestinationsarrayoptionalREPLACES the full destination list when provided. Each entry:functionColumnstringoptionalField to aggregate ("" to clear)functionTypestringoptionalAggregator - one of Count, CountDistinct, CountDistinctKey, Min, Avg, P50, P90, P95, P99, Max, SumgroupByarrayoptionalArray of dimension keys to alert per-group ([] to clear)investigationCooldownSecondsnumberoptionalminimum gap between automatic investigations. Keep at or above thresholdCooldown so a chatty alert doesn't re-investigate the same conditioninvestigationPermissionModestringoptional"read" investigates and reports; "read-write" additionally lets the investigation open a PRinvestigationPromptstringoptionalextra standing instructions prepended to each investigationinvestigationRepositoriesarrayoptionalrepos the investigation may read. Without these it cannot correlate a firing against a recent deploymessageContentstringoptionalCustom notification message ("" to clear)namestringoptionalNew name for the alertproductTypestringoptionalData source - one of Logs, Traces, Errors, Sessions, Metrics, EventsquerystringoptionalFilter query string ("" to clear)thresholdConditionstringoptional"Above", "Below", or "Outside"thresholdCooldownnumberoptionalSeconds between re-notifications while alertingthresholdTypestringoptional"Constant" or "Anomaly"thresholdValuenumberoptionalNew threshold to compare againstthresholdWindownumberoptionalEvaluation window in secondslaunchdarklymcp_update_flag_settings#Update a feature flag's global settings such as name, description, tags, temporary status, and maintainer.4 params
Update a feature flag's global settings such as name, description, tags, temporary status, and maintainer.
flagKeystringrequiredNo description.instructionsarrayrequiredNo description.projectKeystringrequiredNo description.commentstringoptionalNo description.launchdarklymcp_update_individual_targets#Add or remove specific users or contexts from individual flag targeting. Individual targets are the highest priority: they override all rules. Supported instruction kinds: addTargets, removeTargets, replaceTargets. To target non-user context kinds (e.g. organization), include contextKind on the instruction (e.g. { kind: 'addTargets', contextKind: 'organization', values: ['org-123'], variationId: '<id>' }). Note: addContextTargets and removeContextTargets are NOT supported by the LD API; use addTargets/removeTargets with contextKind instead. Responses truncate long lists. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-approval-request` with the returned instructions to submit it for review.5 params
Add or remove specific users or contexts from individual flag targeting. Individual targets are the highest priority: they override all rules. Supported instruction kinds: addTargets, removeTargets, replaceTargets. To target non-user context kinds (e.g. organization), include contextKind on the instruction (e.g. { kind: 'addTargets', contextKind: 'organization', values: ['org-123'], variationId: '<id>' }). Note: addContextTargets and removeContextTargets are NOT supported by the LD API; use addTargets/removeTargets with contextKind instead. Responses truncate long lists. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-approval-request` with the returned instructions to submit it for review.
envstringrequiredEnv for this operation.flagKeystringrequiredFlag Key for this operation.instructionsarrayrequiredInstructions for this operation.projectKeystringrequiredProject Key for this operation.commentstringoptionalComment for this operation.launchdarklymcp_update_playground#Update an LLM playground's name, variants, or archived status. All fields are optional.5 params
Update an LLM playground's name, variants, or archived status. All fields are optional.
playgroundIdstringrequiredPlayground Id for this operation.projectKeystringrequiredProject Key for this operation.archivedbooleanoptionalArchived for this operation.namestringoptionalName for this operation.variantsarrayoptionalVariants for this operation.launchdarklymcp_update_prerequisites#Add or remove prerequisites for a flag in a specific environment. Prerequisites are other flags that must evaluate to specific variations before this flag is evaluated. Use addPrerequisite to migrate prerequisites onto a new flag, or removePrerequisite + addPrerequisite to update dependent flags to point to a new key. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-approval-request` with the returned instructions to submit it for review.5 params
Add or remove prerequisites for a flag in a specific environment. Prerequisites are other flags that must evaluate to specific variations before this flag is evaluated. Use addPrerequisite to migrate prerequisites onto a new flag, or removePrerequisite + addPrerequisite to update dependent flags to point to a new key. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-approval-request` with the returned instructions to submit it for review.
envstringrequiredEnv for this operation.flagKeystringrequiredFlag Key for this operation.instructionsarrayrequiredInstructions for this operation.projectKeystringrequiredProject Key for this operation.commentstringoptionalComment for this operation.launchdarklymcp_update_prompt_snippet#Update an existing prompt snippet. Creates a new version of the snippet. All fields are optional — only provided fields are updated.6 params
Update an existing prompt snippet. Creates a new version of the snippet. All fields are optional — only provided fields are updated.
projectKeystringrequiredProject Key for this operation.snippetKeystringrequiredSnippet Key for this operation.descriptionstringoptionalDescription for this operation.namestringoptionalName for this operation.tagsarrayoptionalTags for this operation.textstringoptionalText for this operation.launchdarklymcp_update_rollout#Change the default rule (fallthrough) for a flag. Set a percentage rollout across variations or serve a single variation to all unmatched users. Weights must sum to 100. Use human-friendly percentages (e.g., 80 for 80%). If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-approval-request` with the returned instructions to submit it for review.8 params
Change the default rule (fallthrough) for a flag. Set a percentage rollout across variations or serve a single variation to all unmatched users. Weights must sum to 100. Use human-friendly percentages (e.g., 80 for 80%). If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-approval-request` with the returned instructions to submit it for review.
envstringrequiredEnv for this operation.flagKeystringrequiredFlag Key for this operation.projectKeystringrequiredProject Key for this operation.rolloutTypestringrequiredRollout Type for this operation.commentstringoptionalComment for this operation.contextKindstringoptionalContext Kind for this operation.variationIndexnumberoptionalVariation Index for this operation.weightsarrayoptionalWeights for this operation.launchdarklymcp_update_segment_rules#Add, remove, or modify attribute-based targeting rules on a segment. Rules evaluate context attributes to determine segment membership. Clauses within a rule are ANDed; multiple rules use OR logic. Supported kinds: addRule, removeRule, addClauses, removeClauses, updateClause, addValuesToClause, removeValuesFromClause, reorderRules, updateRuleDescription, updateRuleRolloutAndContextKind. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-approval-request` with the returned instructions to submit it for review.5 params
Add, remove, or modify attribute-based targeting rules on a segment. Rules evaluate context attributes to determine segment membership. Clauses within a rule are ANDed; multiple rules use OR logic. Supported kinds: addRule, removeRule, addClauses, removeClauses, updateClause, addValuesToClause, removeValuesFromClause, reorderRules, updateRuleDescription, updateRuleRolloutAndContextKind. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-approval-request` with the returned instructions to submit it for review.
environmentKeystringrequiredEnvironment Key for this operation.instructionsarrayrequiredInstructions for this operation.projectKeystringrequiredProject Key for this operation.segmentKeystringrequiredSegment Key for this operation.commentstringoptionalComment for this operation.launchdarklymcp_update_segment_targets#Add or remove individual context keys from a segment's included or excluded lists. Included targets always match the segment. Excluded targets never match, even if rules would include them. Supported kinds: addIncludedTargets, removeIncludedTargets, addExcludedTargets, removeExcludedTargets. Each instruction requires contextKind and values. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-approval-request` with the returned instructions to submit it for review.5 params
Add or remove individual context keys from a segment's included or excluded lists. Included targets always match the segment. Excluded targets never match, even if rules would include them. Supported kinds: addIncludedTargets, removeIncludedTargets, addExcludedTargets, removeExcludedTargets. Each instruction requires contextKind and values. If the environment requires approval, the response includes requiresApproval: true and the attempted instructions; call `create-approval-request` with the returned instructions to submit it for review.
environmentKeystringrequiredEnvironment Key for this operation.instructionsarrayrequiredInstructions for this operation.projectKeystringrequiredProject Key for this operation.segmentKeystringrequiredSegment Key for this operation.commentstringoptionalComment for this operation.launchdarklymcp_update_targeting_rules#Add, remove, or modify custom targeting rules for a flag in an environment. Rules evaluate top-to-bottom; first matching rule wins. Use get-flag to look up rule _ids, clause _ids, and variation _ids before constructing instructions.5 params
Add, remove, or modify custom targeting rules for a flag in an environment. Rules evaluate top-to-bottom; first matching rule wins. Use get-flag to look up rule _ids, clause _ids, and variation _ids before constructing instructions.
envstringrequiredEnv for this operation.flagKeystringrequiredFlag Key for this operation.instructionsarrayrequiredInstructions for this operation.projectKeystringrequiredProject Key for this operation.commentstringoptionalComment for this operation.launchdarklymcp_updateagentgraph#Update an agent graph's metadata or structure. All fields are optional. If rootConfigKey or edges are provided, both must be present and will fully replace the existing graph structure. Pass name or description to update metadata only.6 params
Update an agent graph's metadata or structure. All fields are optional. If rootConfigKey or edges are provided, both must be present and will fully replace the existing graph structure. Pass name or description to update metadata only.
graphKeystringrequiredGraph Key for this operation.projectKeystringrequiredProject Key for this operation.descriptionstringoptionalDescription for this operation.edgesarrayoptionalEdges for this operation.namestringoptionalName for this operation.rootConfigKeystringoptionalRoot Config Key for this operation.launchdarklymcp_updateexperiment#Update fields on an experiment or its current iteration. Which fields are mutable depends on the current iteration's status (not_started, running, stopped). This tool first reads the experiment's mutableFieldsByStatus, applies only the updates that are allowed for the current status via the updateExperimentFields semantic patch, and returns any rejected fields under `skipped` with the reason. If no provided field is mutable, the response includes `currentStatus` and `allowedFields` so you can retry with valid inputs.22 params
Update fields on an experiment or its current iteration. Which fields are mutable depends on the current iteration's status (not_started, running, stopped). This tool first reads the experiment's mutableFieldsByStatus, applies only the updates that are allowed for the current status via the updateExperimentFields semantic patch, and returns any rejected fields under `skipped` with the reason. If no provided field is mutable, the response includes `currentStatus` and `allowedFields` so you can retry with valid inputs.
environmentKeystringrequiredEnvironment Key for this operation.experimentKeystringrequiredExperiment Key for this operation.projectKeystringrequiredProject Key for this operation.analysisConfigobjectoptionalAnalysis Config for this operation.attributesarrayoptionalAttributes for this operation.canReshuffleTrafficbooleanoptionalCan Reshuffle Traffic for this operation.covariateIdstringoptionalCovariate Id for this operation.dataSourcestringoptionalData Source for this operation.descriptionstringoptionalDescription for this operation.flagsobjectoptionalFlags for this operation.flagSettingsobjectoptionalFlag Settings for this operation.holdoutIdstringoptionalHoldout Id for this operation.hypothesisstringoptionalHypothesis for this operation.maintainerIdstringoptionalMaintainer Id for this operation.methodologystringoptionalMethodology for this operation.metricsarrayoptionalMetrics for this operation.namestringoptionalName for this operation.primaryFunnelKeystringoptionalPrimary Funnel Key for this operation.primarySingleMetricKeystringoptionalPrimary Single Metric Key for this operation.randomizationUnitstringoptionalRandomization Unit for this operation.tagsarrayoptionalTags for this operation.treatmentsarrayoptionalTreatments for this operation.launchdarklymcp_vent#Report a missing capability, bug, parameter gap, or unclear error encountered while using LaunchDarkly MCP tools. This feedback is collected and triaged to improve the toolset. Use this when a tool is missing, returns an unexpected error, or lacks a needed parameter.5 params
Report a missing capability, bug, parameter gap, or unclear error encountered while using LaunchDarkly MCP tools. This feedback is collected and triaged to improve the toolset. Use this when a tool is missing, returns an unexpected error, or lacks a needed parameter.
categorystringrequiredThe category of the issue being reported.descriptionstringrequiredA description of the issue or missing capability.contextstringoptionalAdditional context about the situation when the issue occurred.errorMessagestringoptionalThe error message received, if any.toolNamestringoptionalThe name of the tool that has the issue, if applicable.