drio
Open app

Databricks MCP Server

Source

Databricks MCP Server

Catalog onlyCatalog onlySTDIO

Overview

Mcp Databricks Server is a Model Context Protocol (MCP) server designed for executing SQL queries against Databricks using the Statement Execution API. It allows AI assistants to directly query Databricks data warehouses, analyze database schemas, and retrieve query results in a structured format while adhering to permission boundaries.

To use the server, install the required dependencies, set up your environment variables with your Databricks credentials, and run the server in standalone mode or configure it with Cursor for AI assistance.

  • Execute SQL queries on Databricks. - List available schemas in a catalog. - List tables in a schema. - Describe table schemas. - Handle long-running queries with polling.
  1. Executing complex SQL queries on large datasets.
  2. Analyzing database schemas for better data management.
  3. Integrating with AI assistants for automated data retrieval.

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

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

Claude Code

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

.mcp.json (project root)

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

VS Code (Copilot)

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

.vscode/mcp.json

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

Windsurf

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

~/.codeium/windsurf/mcp_config.json

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

Cline

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

Cline MCP Settings (via UI)

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

FAQ

What are the system requirements?

Python 3.10+ is required along with necessary dependencies.

How do I set up permissions?

Ensure that the user associated with the provided token has appropriate permissions for SQL warehouse access and data access.

Can I run long queries?

Yes, the server is designed to handle long-running queries with a default timeout of 10 minutes.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":2324,"uuid":"4838089a-12d3-49f6-86bf-6367cc395825","name":"mcp-databricks-server","title":"Databricks MCP Server","description":"Databricks MCP Server","avatar_url":"https://avatars.githubusercontent.com/u/15639462?v=4","created_at":"2025-03-10T03:43:35.099Z","updated_at":"2025-03-12T11:48:30.725Z","status":"created","author_name":"RafaelCartenet","author_avatar_url":"https://avatars.githubusercontent.com/u/15639462?v=4","tags":"[]","category":"research-and-data","is_featured":false,"sort":1,"url":"https://github.com/RafaelCartenet/mcp-databricks-server","target":"_self","content":"$29","summary":"$2a","img_url":"https://github.com/RafaelCartenet/mcp-databricks-server/raw/main/assets/schema_description.png","type":null,"metadata":"{\"star\":\"9\",\"license\":\"MIT license\",\"language\":\"Python\",\"is_official\":false,\"latest_commit_time\":\"2025-06-03 15:51:44\"}","user_uuid":"b483ba63-a85a-41bf-b172-5d7a3edc39cd","tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]

Research and data