Databricks MCP Server

Enables interaction with Databricks clusters, jobs, and notebooks via the Model Completion Protocol.

Local serverstdioPython★ 49

What is the Databricks MCP Server?

Enables interaction with Databricks clusters, jobs, and notebooks via the Model Completion Protocol.

What you get

A production-ready Model Context Protocol (MCP) server that exposes Databricks REST capabilities to MCP-compatible agents and tooling. Version 0.4.4 introduces structured responses, resource caching, retry-aware networking, and end-to-end resilience improvements.

Configuration and credentials

  • Python 3.10+ - uv for dependency management and publishing

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

How to install the Databricks MCP Server

{
  "mcpServers": {
    "databricks-mcp-local": {
      "command": "uvx",
      "args": ["databricks-mcp-server@latest"],
      "env": {
        "DATABRICKS_HOST": "https://your-workspace.databricks.com",
        "DATABRICKS_TOKEN": "dapiXXXXXXXXXXXXXXXX",
        "DATABRICKS_WAREHOUSE_ID": "sql_warehouse_12345",
        "RUNNING_VIA_CURSOR_MCP": "true"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Python 3.10+ - uv for dependency management and publishing
VariableDescriptionRequired
DATABRICKS_HOSTEndpoint or connection string the server talks to.Optional
DATABRICKS_TOKENCredential the server authenticates with.Yes
DATABRICKS_WAREHOUSE_IDConfiguration value read at startup.Optional
RUNNING_VIA_CURSOR_MCPConfiguration value read at startup.Optional
TOOL_TIMEOUT_SECONDSConfiguration value read at startup.Optional
MAX_CONCURRENT_REQUESTSConfiguration value read at startup.Optional
HTTP_TIMEOUT_SECONDSConfiguration value read at startup.Optional
API_MAX_RETRIESConfiguration value read at startup.Optional

Example prompts to try

  • “Use Databricks to Category.”
  • “Use Databricks to Clusters.”
  • “Use Databricks to Jobs.”

Frequently asked questions

You can use LLMs to manage Databricks clusters (create, terminate, start), execute jobs, list notebooks, run SQL queries, and more. Essentially, automate many of your Databricks workflows.