How to Use the Databricks MCP in VS Code Copilot

Q: How can I give my whole team access to Databricks from VS Code Copilot?

Add the MCP Server configuration to a .vscode/mcp.json file and commit it to your Git repository. Every team member who pulls the repo will automatically have the Databricks tools available in Copilot.

Q: Can my team explore our Databricks Unity Catalog using VS Code Copilot?

They can. The agent can use the listcatalogs and listschemas tools to browse your data assets. This is a great way for developers to discover data without leaving VS Code.

Connect your entire engineering team to Databricks, right inside VS Code Copilot.

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 VS Code Copilot

Create your Vinkius account to connect Databricks to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Standardize Databricks Access for Your Team

Check a `.vscode/mcp.json` file into your repository, and your whole team gets the same tools. Every developer's Copilot agent can now answer questions about your shared Databricks environment, ensuring everyone is working with the same information. A new engineer can ask, 'What clusters are available for performance testing?' and get a live answer from `list_clusters`. This replaces outdated wiki pages with a direct line to the API.

Write Consistent Operational Scripts

Now the whole team generates deployment scripts the same way. When Copilot writes a script, it can use `list_jobs` to get the correct, up-to-date job ID. This simple check cuts down on 'works on my machine' errors during deployment. Your agent can also check on available SQL warehouses with `list_warehouses` to make sure new analytics queries are routed correctly. This MCP server gives every developer's agent the same operational picture of your infrastructure.

Safe, Read-Only Exploration in VS Code

This server provides a secure, read-only window into your Databricks configuration. Your team can use Copilot to explore the Unity Catalog with `list_catalogs` and `list_schemas` or audit job history with `list_job_runs`. It's a safe way to give Copilot helpful visibility. Your agent can find data and check system status without needing dangerous write permissions, all from the editor your team already uses.

Setup guide

Set up Databricks MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Databricks MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Databricks tools listed. Try asking: "List my recent Databricks transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

Add the MCP Server configuration to a `.vscode/mcp.json` file and commit it to your Git repository. Every team member who pulls the repo will automatically have the Databricks tools available in Copilot.

Yes. When you ask Copilot to write a script that interacts with a job, it can call the `list_jobs` tool to fetch the current ID. This ensures the scripts it generates are accurate.

They can. The agent can use the `list_catalogs` and `list_schemas` tools to browse your data assets. This is a great way for developers to discover data without leaving VS Code.

Yes. The server only performs read-only operations. All connections are managed by Vinkius's SOC 2 compliant, zero-trust infrastructure, making it suitable for enterprise environments.

Only metadata is ever read. This includes information like cluster names, job run history, and schema definitions from your Unity Catalog. Your actual lakehouse data is never touched or transferred. Each request is handled in a dedicated, ephemeral environment.

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