Databricks

Databricks MCP Connector for Claude

A+

Manage lakehouse via Databricks — monitor compute clusters, track job executions, audit SQL warehouses, and explore Unity Catalog directly from any AI agent.

8 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Connect your Databricks workspace to any AI agent and take full control of your data intelligence platform and lakehouse orchestration through natural conversation.

What you can do

  • Cluster Monitoring — List all compute nodes and retrieve detailed information for specific clusters to audit health and capacity limits
  • Job Orchestration — List all configured workflows and jobs, and monitor recent executions to verify data pipeline statuses
  • SQL Warehouse Management — Enumerate explicitly configured SQL Serverless warehouses and track their active operational boundaries
  • Unity Catalog Exploration — List root catalogs and detailed schemas/databases to identify exactly where your structured data resides
  • Identity Oversight — Fetch profile information for the authenticated user or service principal to verify active workspace permissions
  • Run Auditing — Retrieve chronological logs of job runs to identify precise points of failure in your complex data workflows

How it works

  1. Subscribe to this server
  2. Enter your Databricks Host URL and Personal Access Token (PAT)
  3. Start managing your lakehouse from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • Data Engineers — monitor job runs and cluster health without leaving the development environment
  • Analytics Engineers — explore Unity Catalog schemas and verify SQL warehouse availability in real-time
  • Data Platform Teams — audit workspace resources and monitor active service principal identities
  • MLOps Engineers — track model training jobs and verify compute cluster configurations through natural language
lakehousedata-engineeringcluster-managementsql-warehousingdata-governancebig-data

8 tools expose this connector's capabilities to your AI agent.

list_clusters

List all clusters from Databricks

get_cluster

Get cluster details from Databricks

list_jobs

List all jobs from Databricks

list_job_runs

List job runs from Databricks

list_warehouses

List SQL warehouses from Databricks

list_catalogs

List Unity Catalog catalogs from Databricks

list_schemas

List schemas in catalog from Databricks

get_me

Get current user from Databricks

See how to talk to your AI agent using Databricks.

List all compute clusters in my workspace

I found 3 clusters: 'Standard-ETL-Cluster' (Running), 'ML-Training-Node' (Terminated), and 'Shared-Dev-Pool' (Running). Would you like to see the detailed specs for any of these?

Show me the last 5 runs for job 'Daily-Sales-ETL'

Retrieving runs for 'Daily-Sales-ETL'... The most recent (ID: 987) finished successfully at 6:00 AM. Run 985 failed due to a cluster timeout. I can pull the detailed error logs if you'd like.

List all catalogs in Unity Catalog

I found 4 root catalogs: 'main', 'development', 'samples', and 'system'. Which one would you like to explore for databases and schemas?

Yes. Provide the 'job_id' to the 'list_job_runs' tool. The agent will retrieve the chronological history of executions, allowing you to identify successful completions or precise points of failure in your workflows.

Related Connectors