How to Use the DataRobot MCP in VS Code Copilot

Q: How does my team share DataRobot in VS Code Copilot?

Commit a .vscode/mcp.json file containing your Vinkius server URL to your Git repository. Anyone who pulls the repo gets immediate access to the tools.

Q: Can VS Code Copilot test DataRobot deployments?

Copilot uses listdeployments to find your active endpoints. You then ask it to write and execute HTTP requests against those prediction servers.

Share DataRobot deployment status across your entire engineering team using 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 DataRobot MCP to VS Code Copilot

Create your Vinkius account to connect DataRobot 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 DataRobot with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Access DataRobot projects in VS Code Copilot

Bringing active machine learning builds into the IDE panel starts with `list_projects`. Copilot reads the project list and helps you locate the specific predictive models your application needs to call. Engineers stop shoulder-tapping data scientists to figure out which environment is ready. Digging deeper into target variables involves `get_project`. The AI client formats this into markdown summaries that you drop directly into pull request descriptions. Entire teams stay aligned on ML progress without leaving their code environment.

Audit ML endpoints via MCP Server

Returning active prediction URLs requires `list_deployments`. VS Code Copilot uses this data to scaffold integration tests that point to the correct endpoints automatically. QA processes speed up significantly when the test suite writes itself based on real infrastructure. Understanding behavior means pulling algorithm details with `get_model`. Your agent translates those JSON responses into documented inline comments above your API calls. Future maintainers know exactly why a specific payload structure exists.

Review training inputs collectively

Revealing raw information from training models happens through `list_datasets`. Copilot cross-references these dataset schemas against your application's database models to spot missing columns. Data mismatches get caught during development, long before production deployment. Checking `list_models` exposes the full leaderboard of algorithms tested against that data. Instructing the AI to build a status dashboard in your internal admin panel using the live leaderboard stats takes minutes. Everyone gets visibility into the machine learning pipeline.

Setup guide

Set up DataRobot 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 DataRobot 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 DataRobot tools listed. Try asking: "List my recent DataRobot transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "datarobot-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 DataRobot. 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 DataRobot 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 DataRobot MCP in VS Code Copilot

Commit a `.vscode/mcp.json` file containing your Vinkius server URL to your Git repository. Anyone who pulls the repo gets immediate access to the tools.

Copilot uses `list_deployments` to find your active endpoints. You then ask it to write and execute HTTP requests against those prediction servers.

Vinkius handles all authentication through a single endpoint token while running requests in ephemeral V8 Isolate Sandboxes. Your organization maintains strict control over API credentials.

Developers request accuracy scores and error rates by having the agent run `get_model`. The IDE displays these metrics directly in the chat window.

Execution happens within Vinkius's zero-trust architecture. When `list_datasets` retrieves schema information or row counts, the data travels securely to the authorized IDE and never persists in the middle layer.

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