How to Use the Databricks MCP in Claude

Manage your Databricks lakehouse from the Claude Desktop app or claude.ai without writing a single script.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Databricks MCP to Claude Desktop

Create your Vinkius account to connect Databricks to Claude Desktop and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Databricks with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Check Cluster and Job Status Instantly

This toolset lets you ask Claude what's happening inside Databricks. Your agent uses `list_clusters` and `list_jobs` to give you a live status report right in the chat. You get a quick, plain-English summary of all active compute and running jobs. Then you can dig deeper. Ask about a specific job and your agent will use `list_job_runs` to pull its history. See what failed, what succeeded, and how long it took. It's faster than switching to the Databricks UI just to check on a pipeline.

Explore Your Unity Catalog with Claude

Map out your entire data lakehouse from the chat prompt. Your agent can call `list_catalogs` and then `list_schemas` to show you exactly what data is available. It’s a fast way to discover datasets you didn't know existed. This makes data accessible to everyone, not just engineers. A project manager can ask, “What customer data do we have in the production catalog?” and get a real answer. No more waiting for someone to run a query for them.

Manage Warehouses and Users from Chat

The Databricks MCP Server gives your agent simple admin tools. Use `get_me` to confirm which user your agent is authenticated as. Then, use `list_warehouses` to see all the SQL warehouses you can access. These tools are great for quick sanity checks before you run something expensive. Ask Claude which warehouse is sized for large queries, and it'll check the list. You get the right answer without having to click through settings menus.

Setup guide

Set up Databricks MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Databricks MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Databricks MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under databricks-mcp.

json

{
  "mcpServers": {
    "databricks-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Databricks. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Databricks now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Databricks MCP in Claude Desktop

Just ask your agent, 'List all active clusters in Databricks.' It will use the `list_clusters` tool to get a live report and show it to you directly in the chat window.

Yes. When you ask Claude to show you your jobs, it uses the `list_jobs` tool to pull a complete list. You can then ask for the run history of a specific job.

Absolutely. You can ask your agent to list all catalogs and then list the schemas within a specific catalog. It's a conversational way to navigate your data assets.

If you're using the Claude Desktop app, install the extension from the settings menu for one-click setup. If you're on the web, just paste the Vinkius MCP server URL into the Custom Connectors section of your settings.

This server only reads metadata: cluster names, job IDs, schema names, and user info. No actual table data is ever touched. Your connection is secured by Vinkius's zero-trust platform, and each request runs in an ephemeral sandbox that is destroyed after execution.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript