Databricks MCP Server

A Model Context Protocol (MCP) server that interfaces with the Databricks API, enabling LLMs to execute SQL queries, list jobs, and retrieve job statuses.

Features

• Executes SQL queries on Databricks SQL warehouses.
• Lists all Databricks jobs.
• Retrieves the status of specific Databricks jobs.
• Provides detailed information about Databricks jobs.

Running the Server

Start the server with python main.py. Test using npx @modelcontextprotocol/inspector python3 main.py.

Available MCP Tools

Includes tools like run_sql_query(sql: str), list_jobs(), get_job_status(job_id: int), and get_job_details(job_id: int).

Example Usage with LLMs

Enables natural language interaction with Databricks, allowing LLMs to execute tasks like querying tables, counting records, listing jobs, and checking job statuses.