mcp-databricks-server

32

The Databricks MCP Server is designed to facilitate interaction with Databricks using the Model Context Protocol, enabling LLMs to run SQL queries and manage jobs via an API connection. It supports various job management functionalities and SQL command execution within a Databricks environment.

Databricks MCP Server

A Model Context Protocol (MCP) server that connects to Databricks API, allowing LLMs to interact with Databricks through SQL queries and job management.

Features

  • Run SQL queries on Databricks SQL warehouses
  • List all Databricks jobs
  • Get status and detailed information of specific Databricks jobs

Prerequisites

  • Python 3.7+
  • Databricks workspace with personal access token and SQL warehouse endpoint

Running the Server

Start the MCP server and test using the inspector.

Available MCP Tools

  • Execute SQL queries
  • List and manage jobs

Troubleshooting

  • Verify Databricks host and permissions
  • Use the test script for connection verification.

Security Considerations

  • Protect personal access tokens and secure environment setup