▌BestMCPTools.org
Databricks MCP logo

Databricks MCP

Query Unity Catalog, run notebooks and inspect jobs from an AI agent.

DatabaseFreeClaudeClaude CodeCursorVS CodeAll ModelsModerate✓ Verified
Visit Tool

Last verified: September 20, 2026

Own Databricks MCP? Boost it to the top.✦ Upgrade to Featured

Maintenance status

Repository link unavailable
Checked September 28, 2026

The GitHub link we had for this server no longer resolves.

How to Install Databricks MCP

$npx -y @databricks/mcp

Requires Claude Desktop, Cursor, Windsurf, or another MCP-compatible client.

Setup by client

Claude Desktop (claude_desktop_config.json)

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

Cursor (~/.cursor/mcp.json)

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

VS Code (.vscode/mcp.json)

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

Claude Code (terminal)

claude mcp add databricks-mcp -- npx -y @databricks/mcp

Add any API keys or environment variables the server's README lists.

About Databricks MCP

The Databricks MCP server exposes the lakehouse to an AI agent: browsing Unity Catalog schemas, running SQL against warehouses, triggering notebooks and inspecting job runs. Because Unity Catalog governs access, the agent inherits existing permissions rather than bypassing them, which is the main reason data teams are willing to wire an assistant into production data at all. It is most useful for exploratory analysis and pipeline debugging rather than unattended writes. Teams on a cloud data warehouse can use the Snowflake MCP setup, and the Tableau MCP setup lets agents read the dashboards built on top.

Key Features

  • lakehouse
  • unity-catalog
  • sql
  • data-engineering
  • notebooks

Pricing

Free: from Free (Databricks workspace required)

Pros & Cons

Pros

  • Lets the assistant write and run real queries instead of guessing
  • Read-only mode is safe to point at production-shaped data
  • Skips most ORM and CSV-shuffling boilerplate

Cons

  • Misconfigured permissions can expose sensitive data
  • Long-running queries need explicit timeouts
  • Schema drift requires reconnecting or refreshing context

Best For

  • Ad-hoc analytics without a BI tool
  • Drafting migrations and reviewing query plans
  • Letting non-SQL teammates ask questions of a database
  • Bootstrapping internal admin workflows

Our Take on Databricks MCP

The right server if your data already lives in Databricks. Unity Catalog governance is what makes it safe to point an agent at; without a Databricks workspace it is irrelevant.

Frequently Asked Questions

Tags

#Database#lakehouse#unity-catalog#sql#data-engineering#notebooks