databricks-mcp
If you are the rightful owner of databricks-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
MCP Databricks is a powerful integration for AI assistants to manage Databricks environments using the Model Context Protocol.
MCP Databricks is designed to seamlessly connect AI assistants to Databricks workspaces through the Model Context Protocol (MCP). Built with Python, it offers a comprehensive suite of tools for managing various aspects of a Databricks environment. This server allows AI assistants to manage compute resources, execute SQL queries, organize workspace objects, and more. It requires Python 3.11 or higher, a Databricks workspace, and a personal access token for authentication. The server can be deployed using Docker for production environments or locally with uv for development purposes. It supports stdio transport for compatibility with MCP clients like Claude Desktop.
Features
- Cluster Management: Tools for listing, creating, deleting, and managing Databricks clusters.
- Library Management: Install various types of libraries on running clusters.
- Command Execution: Execute commands in Python, Scala, or SQL on Databricks clusters.
- SQL Warehouse Management: Manage SQL warehouses with tools for listing and creating them.
- Workspace Objects: Manage workspace objects with tools for importing, deleting, and creating directories.
