Databricks MCP — Install & Live Demo

Live Demo

What it looks like in practice

mcp-databricks-server.replay ▶ ready

0/0

Install

Pick your client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

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

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

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

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "mcp-databricks-server",
      "command": "npx",
      "args": [
        "-y",
        "mcp-databricks-server"
      ]
    }
  ]
}

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

{
  "context_servers": {
    "mcp-databricks-server": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "mcp-databricks-server"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

claude mcp add mcp-databricks-server -- npx -y mcp-databricks-server

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use Databricks MCP

Get started with Databricks MCP

When to use: When you want to bring Databricks MCP into your Claude workflow.

Flow

Install the MCP server in your client (see Install tab).
Authenticate or configure required tokens.
Ask Claude to use the new tools.

Use Databricks MCP to help me with a task.✓ Copied

Outcome: Claude can interact with Databricks MCP directly from your IDE.

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills