Prisma MCP

1. Install the SDK

   Node.js

   npm install @scalekit-sdk/node

   Python

   pip install scalekit

   Full SDK reference: Node.js | Python

2. Set your credentials

   Add your Scalekit credentials to your .env file. 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>

3. Authorize and make your first call

   Node.js

   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.actions
   
   const connector = 'prismamcp'
   const identifier = 'user_123'
   
   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Prisma MCP:', link)
   process.stdout.write('Press Enter after authorizing...')
   await new Promise(r => process.stdin.once('data', r))
   
   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'prismamcp_fetch_workspace_details',
     toolInput: {},
   })
   console.log(result)

   Python

   quickstart.py

   import os
   from scalekit.client import ScalekitClient
   from dotenv import load_dotenv
   load_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.actions
   
   connection_name = "prismamcp"
   identifier = "user_123"
   
   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Prisma MCP:", link_response.link)
   input("Press Enter after authorizing...")
   
   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="prismamcp_fetch_workspace_details",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)

What you can do

Connect this agent connector to let your agent:

• Search prisma documentation — Search Prisma’s official documentation and knowledge sources to answer questions about Prisma Postgres, Prisma ORM, Accelerate, Optimize, schema design, and migrations
• List object store buckets, prisma postgres databases, prisma postgres connection strings — List object-store buckets in the workspace, 100 per page, optionally filtered by project ID
• Delete object store bucket key, object store bucket, prisma postgres database — Delete an object-store bucket access key
• Create object store bucket key, object store bucket, prisma postgres recovery — Create an S3-compatible access key for an object-store bucket
• Schema introspect database — Introspect and return the schema of a Prisma Postgres database as JSON
• Fetch workspace details — Retrieve details of the current Prisma Postgres workspace, including plan limits and usage

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.

prismamcp_create_object_store_bucket#Create a new object-store bucket in the given project. On success, use the returned bucket id to generate access credentials.3 params▾

Create a new object-store bucket in the given project. On success, use the returned bucket id to generate access credentials.

NameTypeRequiredDescription

projectIdstringrequiredThe project ID to create the bucket in (e.g. proj_xxx).

branchIdstringoptionalBranch ID (e.g. br_xxx) to scope the bucket to. Defaults to the project default branch.

namestringoptionalA display name for the bucket. Generated if omitted.

prismamcp_create_object_store_bucket_key#Create an S3-compatible access key for an object-store bucket. The secret access key is returned exactly once and never stored, so it must be saved immediately.3 params▾

Create an S3-compatible access key for an object-store bucket. The secret access key is returned exactly once and never stored, so it must be saved immediately.

NameTypeRequiredDescription

bucketIdstringrequiredThe bucket ID to create the key for (e.g. bkt_xxx). Use the List Buckets tool to find it.

rolestringrequiredAccess level: 'read' for read-only, 'read_write' for full access.

namestringoptionalA display name for the key. Generated if omitted.

prismamcp_create_prisma_postgres_backup#Create an automated backup for a Prisma Postgres database. Note: on-demand backup creation is not currently supported; backups are created automatically by the system.2 params▾

Create an automated backup for a Prisma Postgres database. Note: on-demand backup creation is not currently supported; backups are created automatically by the system.

NameTypeRequiredDescription

databaseIdstringrequiredThe unique identifier of the Prisma Postgres database. Get it from List Databases.

projectIdstringrequiredThe unique identifier of the Prisma project. Get it from List Databases.

prismamcp_create_prisma_postgres_connection_string#Create a new connection string for a Prisma Postgres database. Returns both Prisma and direct connection strings when available.2 params▾

Create a new connection string for a Prisma Postgres database. Returns both Prisma and direct connection strings when available.

NameTypeRequiredDescription

databaseIdstringrequiredThe unique identifier of the Prisma Postgres database. Get it from List Databases.

namestringrequiredA unique display name for the resource.

prismamcp_create_prisma_postgres_database#Create a new managed Prisma Postgres database in the specified region.2 params▾

Create a new managed Prisma Postgres database in the specified region.

NameTypeRequiredDescription

namestringrequiredA unique display name for the resource.

regionstringrequiredThe AWS region to deploy the database in. Accepted values: us-east-1, us-west-1, eu-west-3, eu-central-1, ap-northeast-1, ap-southeast-1.

prismamcp_create_prisma_postgres_recovery#Restore a Prisma Postgres database from a backup into a new database.3 params▾

Restore a Prisma Postgres database from a backup into a new database.

NameTypeRequiredDescription

backupIdstringrequiredThe unique identifier of the backup to restore. Get it from List Backups.

databaseIdstringrequiredThe unique identifier of the Prisma Postgres database. Get it from List Databases.

targetDatabaseNamestringrequiredA unique name for the recovered database.

prismamcp_delete_object_store_bucket#Permanently delete an object-store bucket, all objects stored in it, and all its access keys. This action cannot be undone.1 param▾

Permanently delete an object-store bucket, all objects stored in it, and all its access keys. This action cannot be undone.

NameTypeRequiredDescription

bucketIdstringrequiredThe bucket ID to delete (e.g. bkt_xxx). Use the List Buckets tool to find it.

prismamcp_delete_object_store_bucket_key#Delete an object-store bucket access key. The key immediately stops working. This action cannot be undone.1 param▾

Delete an object-store bucket access key. The key immediately stops working. This action cannot be undone.

NameTypeRequiredDescription

bucketKeyIdstringrequiredThe key ID to delete (e.g. bkey_xxx), as returned when the key was created.

prismamcp_delete_prisma_postgres_connection_string#Permanently delete a connection string by its ID. This action cannot be undone.1 param▾

Permanently delete a connection string by its ID. This action cannot be undone.

NameTypeRequiredDescription

idstringrequiredThe unique identifier of the connection string. Get it from List Connection Strings.

prismamcp_delete_prisma_postgres_database#Permanently delete a Prisma Postgres database by its ID. This action cannot be undone.1 param▾

Permanently delete a Prisma Postgres database by its ID. This action cannot be undone.

NameTypeRequiredDescription

databaseIdstringrequiredThe unique identifier of the Prisma Postgres database. Get it from List Databases.

prismamcp_execute_prisma_postgres_schema_update#Execute a DDL schema update on a Prisma Postgres database. Use for schema changes only; use Execute SQL Query for data reads and writes.3 params▾

Execute a DDL schema update on a Prisma Postgres database. Use for schema changes only; use Execute SQL Query for data reads and writes.

NameTypeRequiredDescription

databaseIdstringrequiredThe unique identifier of the Prisma Postgres database. Get it from List Databases.

projectIdstringrequiredThe unique identifier of the Prisma project. Get it from List Databases.

querystringrequiredThe SQL query to execute against the database.

prismamcp_execute_sql_query#Execute a SQL query on a Prisma Postgres database and return the results as JSON. Does not have permission to run schema updates.3 params▾

Execute a SQL query on a Prisma Postgres database and return the results as JSON. Does not have permission to run schema updates.

NameTypeRequiredDescription

databaseIdstringrequiredThe unique identifier of the Prisma Postgres database. Get it from List Databases.

projectIdstringrequiredThe unique identifier of the Prisma project. Get it from List Databases.

querystringrequiredThe SQL query to execute against the database.

prismamcp_fetch_workspace_details#Retrieve details of the current Prisma Postgres workspace, including plan limits and usage.0 params▾

Retrieve details of the current Prisma Postgres workspace, including plan limits and usage.

prismamcp_introspect_database_schema#Introspect and return the schema of a Prisma Postgres database as JSON.2 params▾

Introspect and return the schema of a Prisma Postgres database as JSON.

NameTypeRequiredDescription

databaseIdstringrequiredThe unique identifier of the Prisma Postgres database. Get it from List Databases.

projectIdstringrequiredThe unique identifier of the Prisma project. Get it from List Databases.

prismamcp_list_object_store_buckets#List object-store buckets in the workspace, 100 per page, optionally filtered by project ID. Use the returned id as bucketId in other bucket tools.2 params▾

List object-store buckets in the workspace, 100 per page, optionally filtered by project ID. Use the returned id as bucketId in other bucket tools.

NameTypeRequiredDescription

cursorstringoptionalPagination cursor from a previous response's nextCursor.

projectIdstringoptionalFilter buckets by project ID (e.g. proj_xxx). Omit to list all buckets.

prismamcp_list_prisma_postgres_backups#List all available automated backups for a Prisma Postgres database.1 param▾

List all available automated backups for a Prisma Postgres database.

NameTypeRequiredDescription

databaseIdstringrequiredThe unique identifier of the Prisma Postgres database. Get it from List Databases.

prismamcp_list_prisma_postgres_connection_strings#List all connection strings for a Prisma Postgres database.1 param▾

List all connection strings for a Prisma Postgres database.

NameTypeRequiredDescription

databaseIdstringrequiredThe unique identifier of the Prisma Postgres database. Get it from List Databases.

prismamcp_list_prisma_postgres_databases#List all Prisma Postgres databases in the workspace. Use the returned id as databaseId in other tools.0 params▾

List all Prisma Postgres databases in the workspace. Use the returned id as databaseId in other tools.

prismamcp_search_prisma_documentation#Search Prisma's official documentation and knowledge sources to answer questions about Prisma Postgres, Prisma ORM, Accelerate, Optimize, schema design, and migrations. Returns an answer grounded in the docs, with citations.1 param▾

Search Prisma's official documentation and knowledge sources to answer questions about Prisma Postgres, Prisma ORM, Accelerate, Optimize, schema design, and migrations. Returns an answer grounded in the docs, with citations.

NameTypeRequiredDescription

querystringrequiredNatural-language question about Prisma — Prisma Postgres, Prisma ORM, Accelerate, Optimize, schema design, migrations, etc.