# Does Databricks have an MCP server?

**Yes — Official.** Databricks maintains an official MCP server.

> Endpoints are workspace-relative (https://<workspace>/api/2.0/mcp/…), governed through Unity Catalog — no single global URL.

## Facts

- Verdict: Official (Yes)
- Access: Built into the product — Ships inside the vendor's own app or CLI rather than as a standalone download.
- Endpoint: `Workspace-managed MCP servers — in-product`
- Repository: [databrickslabs/mcp](https://github.com/databrickslabs/mcp) — ★ 94, last push 2025-07-09, NOASSERTION
- Maintainer: Databricks Labs
- Language: Python
- Category: [Data Platforms](https://mcpyet.com/category/data-platforms/)
- Verified against vendor docs: 2026-08-10
- GitHub data refreshed: 2026-08-11 (re-checked every 6 hours)

## The receipts

- **In-product:** Workspace-managed MCP servers — in-product — ships inside Databricks's own product rather than as a standalone server. Documented at <https://docs.databricks.com/aws/en/generative-ai/mcp/>.
- **Official repository:** [databrickslabs/mcp](https://github.com/databrickslabs/mcp) — ★ 94, pushed 2025-07-09, NOASSERTION (stale)

## How to connect it

Ships inside the vendor's own app or CLI rather than as a standalone download.

### Claude Code

```sh
claude mcp add databricks -- npx -y <package-from-readme>
```

Swap in the exact package and flags from the repo README — most servers need an API key passed as an environment variable. Add `--scope user` to make it available in every project.

### Claude Desktop

Open **Settings → Developer → Edit Config** and add the server to `claude_desktop_config.json`, then restart Claude Desktop:

```json
{
  "mcpServers": {
    "databricks": {
      "command": "npx",
      "args": [
        "-y",
        "<package-from-readme>"
      ],
      "env": {
        "API_KEY": "…"
      }
    }
  }
}
```

### Cursor

Add to `.cursor/mcp.json` in your project, or `~/.cursor/mcp.json` for every project:

```json
{
  "mcpServers": {
    "databricks": {
      "command": "npx",
      "args": [
        "-y",
        "<package-from-readme>"
      ],
      "env": {
        "API_KEY": "…"
      }
    }
  }
}
```

### VS Code

Add to `.vscode/mcp.json`, then pick the server from Copilot's agent-mode tools menu:

```json
{
  "servers": {
    "databricks": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "<package-from-readme>"
      ]
    }
  }
}
```

### ChatGPT

ChatGPT connects to **remote servers only**, and this one runs on your machine. Either expose it through an MCP gateway that gives it a public URL, or use a client with native local support (Claude or Cursor).

## How we know

Fully managed vendor-hosted MCP servers (Genie, Vector Search, Databricks SQL, Unity Catalog functions) documented on docs.databricks.com, plus the databrickslabs/mcp companion repo.

- GitHub data refreshed 2026-08-11, then every 6 hours.
- Vendor docs verified on 2026-08-10.
- Corrections: hello@mcpyet.com.

## Also in Data Platforms

- [Tableau](https://mcpyet.com/mcp/tableau.md) — Official (Yes)
- [dbt Labs](https://mcpyet.com/mcp/dbt-labs.md) — Official (Yes)
- [Flowcore.io](https://mcpyet.com/mcp/flowcore.md) — Official (Yes)
- [Sugra Systems, Inc.](https://mcpyet.com/mcp/sugra-systems.md) — Official (Yes)
- [datanika-io](https://mcpyet.com/mcp/datanika-io.md) — Official (Yes)

---

Source: https://mcpyet.com/mcp/databricks/ — data refreshed 2026-08-11