databricks-mcp-server
The Databricks MCP Server is designed to facilitate interaction with Databricks through the Model Completion Protocol (MCP), offering efficient tool registration and async support. It provides various utilities to manage clusters, jobs, notebooks, and SQL execution, integrating seamlessly with Databricks API.
What is the purpose of the Databricks MCP Server?
The Databricks MCP Server allows LLM-powered tools to interact with Databricks environments using the MCP protocol, providing access to clusters, jobs, notebooks, and more.
What are the prerequisites for setting up the Databricks MCP Server?
You need Python 3.10 or higher and the 'uv' package manager to set up the Databricks MCP Server.
How can I start the MCP server?
You can start the MCP server by running the provided startup scripts: ./start_mcp_server.sh for Linux/Mac or ./start_mcp_server.ps1 for Windows.
What tools does the Databricks MCP Server expose?
The server exposes tools for managing clusters, jobs, notebooks, and executing SQL statements, among others.
How can I contribute to the Databricks MCP Server project?
Contributions are welcome! Ensure your code follows the project's coding standards, add tests for new functionality, update documentation, and verify all tests pass before submitting a Pull Request.