How to Use the DataRobot MCP in Windsurf

Q: How does Windsurf Cascade interact with DataRobot projects?

Cascade uses the listprojects tool to view your active machine learning runs. It then decides whether to pull specific run details using getproject based on your prompt.

Q: Can I deploy a model from DataRobot in Windsurf?

Yes, you can track deployments using the listdeployments tool. Cascade chains this tool with local git actions to update your production API routes.

Q: What happens if an AutoML project run fails?

Your agent runs getproject to pull the failure state and error logs. It then analyzes your local training parameters to find the issue.

Drive your DataRobot AutoML pipelines directly from Windsurf's Cascade agent to monitor and deploy models without leaving your editor.

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 Windsurf

Create your Vinkius account to connect DataRobot to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit ML Datasets with Cascade

The `list_datasets` tool pulls raw training data sources directly into your Windsurf workspace. Cascade reads these dataset lists using the MCP protocol to verify that your active training runs match your local schema files before you kick off another training cycle. You do not need to bounce back and forth between your browser and your terminal to check if a file uploaded correctly. Cascade handles the verification by calling the dataset tool, letting you focus on tuning your model architecture.

Track Active AutoML Projects via MCP Server

The `list_projects` and `get_project` tools expose your active DataRobot AutoML runs directly to your IDE. Windsurf reads the project status to determine if an AutoML run finished or if it needs more training time. If a run fails, Cascade automatically grabs the project details to diagnose the error. It checks the logs, matches them against your local training script, and suggests immediate code fixes.

Inspect Models and Deployments

The `list_models`, `get_model`, and `list_deployments` tools give you direct access to model performance metrics and production endpoints. Cascade uses this MCP server to compare accuracy scores across different training runs and flag underperforming deployments. Instead of manually writing custom API scripts to query your endpoints, you let your agent run the comparison. It identifies the best performing model and prepares the deployment configuration file for you.

Setup guide

Set up DataRobot MCP in Windsurf

Prerequisites

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

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the DataRobot MCP

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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my DataRobot payment history." If connected, Cascade will call the DataRobot tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Cascade uses the `list_projects` tool to view your active machine learning runs. It then decides whether to pull specific run details using `get_project` based on your prompt.

Yes, you can track deployments using the `list_deployments` tool. Cascade chains this tool with local git actions to update your production API routes.

No, Windsurf features a one-click install in its built-in MCP Marketplace. Alternatively, you can add the server configuration directly to your `~/.codeium/windsurf/mcp_config.json` file.

Your agent runs `get_project` to pull the failure state and error logs. It then analyzes your local training parameters to find the issue.

The server only routes metadata like dataset names and model scores through a secure V8 isolate sandbox. Your raw training files and sensitive model weights remain locked inside DataRobot's secure 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