Databricks MCP Server logo

Databricks MCP Server

by JordiNeil

A Model Context Protocol (MCP) server that connects to Databricks API, allowing LLMs to run SQL queries, list jobs, and get job status. It enables natural language interaction with your Databricks environment.

View on GitHub

Last updated: N/A

What is Databricks MCP Server?

This is a Model Context Protocol (MCP) server designed to interface with Databricks. It allows Large Language Models (LLMs) to interact with Databricks services, such as running SQL queries, listing jobs, and retrieving job statuses, through a standardized protocol.

How to use Databricks MCP Server?

  1. Clone the repository. 2. Set up a virtual environment and install dependencies. 3. Configure Databricks credentials in a .env file. 4. Start the server using python main.py. 5. Test the server using the inspector by running npx @modelcontextprotocol/inspector python3 main.py. Then, use the available MCP tools via LLM prompts.

Key features of Databricks MCP Server

  • Run SQL queries on Databricks SQL warehouses

  • List all Databricks jobs

  • Get status of specific Databricks jobs

  • Get detailed information about Databricks jobs

Use cases of Databricks MCP Server

  • Enabling LLMs to answer questions about data stored in Databricks

  • Automating Databricks job management through natural language commands

  • Integrating Databricks data and job information into LLM-powered applications

  • Providing a natural language interface for Databricks users

FAQ from Databricks MCP Server

What is the Databricks Host?

Your Databricks instance URL (e.g., your-instance.cloud.databricks.com)

How do I get a Databricks Token?

Create a personal access token in Databricks User Settings under the Developer tab.

Where do I find the HTTP Path?

The HTTP Path is located in the connection details of your SQL warehouse in Databricks.

What if I have connection issues?

Ensure your Databricks host is correct, the SQL warehouse is running, and your personal access token has the necessary permissions. Run the test script.

How do I secure my Databricks token?

Secure your .env file and never commit it to version control. Consider using Databricks token with appropriate permission scopes only.