How to Use the Databricks MCP in Cursor

Q: Can Cursor's agent write Python code using my actual Databricks cluster IDs?

Yes, that's the main benefit. The agent calls listclusters to get live IDs, then injects them directly into the code it generates for you. No more using stale, hardcoded values.

Q: How does Cursor help me find the right table in my Databricks Unity Catalog?

Your agent can use the listcatalogs and listschemas tools to navigate your Unity Catalog. Just ask it to find schemas related to a certain topic, and it will search for you.

Q: Can I use Cursor to debug a failed Databricks job run?

You can. The agent uses the listjobruns tool to fetch the status and history of any job. This helps you quickly identify errors without leaving your editor to check the Databricks UI.

Q: How do I add this server to Cursor?

Create a mcp.json file in your project's .cursor directory. Then, add the Vinkius server URL to the mcpServers configuration. The tools will show up in agent mode automatically.

Let your agent pull live Databricks cluster and job data directly into the code you're writing in Cursor.

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 Cursor

Create your Vinkius account to connect Databricks to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate Code with Real Databricks IDs

Write scripts that work on the first try. Ask your agent to list active clusters with `list_clusters`, then tell it to write a Python script that connects to a specific one. You get code with real, current cluster IDs, not placeholders. This kills the frustrating loop of writing code, running it, and watching it fail because an ID was wrong. Your agent gets live data from the API and generates correct code from the start.

Explore Data Schemas Without Leaving the Editor

Stop guessing schema and table names. Your Cursor agent can use `list_catalogs` and `list_schemas` to find the exact dataset you need. Then, it can generate the Spark SQL to query it. Think of it as having the Databricks Data Explorer built right into your IDE. You can discover and inspect your company's data assets while you're coding, which means less context switching and more focus.

Debug Job Runs from Your Cursor MCP Server

Troubleshoot failed jobs much faster. Tell your agent to get the status of recent job runs with `list_job_runs`. It can pull the error messages and help you debug the problem right in the chat interface, alongside your code. You can also use these tools to build out your CI/CD scripts. Have the agent list all jobs with `list_jobs`, then generate a script to trigger a new run via the Databricks API. This MCP Server gives your agent the context to write truly useful operational code.

Setup guide

Set up Databricks MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Databricks MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Databricks transactions." If the MCP tools are loaded correctly, Cursor will call the Databricks tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

Yes, that's the main benefit. The agent calls `list_clusters` to get live IDs, then injects them directly into the code it generates for you. No more using stale, hardcoded values.

Your agent can use the `list_catalogs` and `list_schemas` tools to navigate your Unity Catalog. Just ask it to find schemas related to a certain topic, and it will search for you.

You can. The agent uses the `list_job_runs` tool to fetch the status and history of any job. This helps you quickly identify errors without leaving your editor to check the Databricks UI.

Create a `mcp.json` file in your project's `.cursor` directory. Then, add the Vinkius server URL to the `mcpServers` configuration. The tools will show up in agent mode automatically.

The server only reads metadata about your Databricks environment, like job run history, cluster configurations, and Unity Catalog names. It never accesses the actual data in your tables. All communication is encrypted and processed within Vinkius's isolated, short-lived sandboxes.

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