drio
Open app

Databricks MCP Server

Source

A Model Completion Protocol (MCP) server for interacting with Databricks services

Catalog onlyCatalog onlySTDIO

Overview

Databricks MCP Server is a Model Completion Protocol (MCP) server designed to facilitate interaction with Databricks services, enabling LLM-powered tools to communicate with Databricks clusters, jobs, notebooks, and more.

To use the Databricks MCP Server, install the required dependencies, set up environment variables for your Databricks instance, and run the server using provided scripts.

  • MCP Protocol Support: Allows LLMs to interact with Databricks. - Databricks API Integration: Access to Databricks REST API functionality. - Tool Registration: Exposes Databricks functionality as MCP tools. - Async Support: Built with asyncio for efficient operation.
  1. Managing Databricks clusters (create, start, terminate).
  2. Running and managing Databricks jobs.
  3. Accessing and exporting notebooks from Databricks.
  4. Executing SQL statements on Databricks.

Add to your AI client

Use these steps to connect Databricks MCP Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "databricks-mcp-server-justtryai": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-databricks-mcp-server-justtryai"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "databricks-mcp-server-justtryai": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-databricks-mcp-server-justtryai"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "databricks-mcp-server-justtryai": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-databricks-mcp-server-justtryai"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "databricks-mcp-server-justtryai": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-databricks-mcp-server-justtryai"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "databricks-mcp-server-justtryai": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-databricks-mcp-server-justtryai"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "databricks-mcp-server-justtryai": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-databricks-mcp-server-justtryai"
      ]
    }
  }
}

FAQ

**What is the MCP protocol?**

The MCP protocol is a communication protocol that allows LLMs to interact with Databricks services.

**What are the prerequisites for installation?**

You need Python 3.10 or higher and the `uv` package manager.

**Is there support for asynchronous operations?**

Yes, the server is built with asyncio for efficient handling of requests.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":2755,"uuid":"270fa70a-1897-415a-9ae1-8efd196c2b62","name":"databricks-mcp-server","title":"Databricks MCP Server","description":"A Model Completion Protocol (MCP) server for interacting with Databricks services","avatar_url":"https://avatars.githubusercontent.com/u/129009237?v=4","created_at":"2025-03-14T01:01:27.724Z","updated_at":"2025-03-14T01:36:34.516Z","status":"created","author_name":"JustTryAI","author_avatar_url":"https://avatars.githubusercontent.com/u/129009237?v=4","tags":"[]","category":"developer-tools","is_featured":false,"sort":1,"url":"https://github.com/JustTryAI/databricks-mcp-server","target":"_self","content":"$29","summary":"$2a","img_url":null,"type":null,"metadata":"{\"star\":\"0\",\"license\":\"\",\"language\":\"Python\",\"is_official\":false,\"latest_commit_time\":\"2025-03-13 14:13:11\"}","user_uuid":null,"tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]