Connect agentic coding environments to MCP servers¶

You can connect your DataRobot MCP server to standard agentic coding environments—such as Cursor, Claude Desktop, and VS Code—to allow AI assistants in those environments to discover and call your MCP tools, prompts, and resources. This enables you to use DataRobot capabilities (e.g., projects, deployments, predictions, third-party tools) directly from your IDE or chat client.

This guide explains how to configure each client to use an MCP server that you run locally or that is deployed to DataRobot. It applies whether your MCP server comes from the DataRobot Agentic Application Template or the DataRobot MCP Template.

前提条件¶

Before configuring your coding environment, ensure that you have:

• A running MCP server (local or deployed):
• ローカル
  • MCP server started via the DataRobot Agentic Application Template (default port 9000) or the DataRobot MCP Template (default port 8080).
  • Base URL (e.g., http://localhost:9000/mcp or http://localhost:8080/mcp).
• デプロイ完了
  • MCP server deployed to DataRobot; you need the MCP endpoint URL (e.g., https://{DATAROBOT_URL}/api/v2/deployments/{DEPLOYMENT_ID}/directAccess/mcp).
  • Base URL (e.g., https://{DATAROBOT_URL}/api/v2/deployments/{DEPLOYMENT_ID}/directAccess/mcp).
• Endpoint and auth
  • "Authorization": "Bearer " (required for authentication with the MCP server)
  • "x-datarobot-api-token": "" (required for tool execution)

To find the endpoint of the deployed MCP server:

* For the [DataRobot MCP Template](https://github.com/datarobot-community/datarobot-mcp-template){ target=_blank }, after deploying run `task infra:info` or check the Pulumi/output step for **MCP_SERVER_MCP_ENDPOINT**.
* For the [Agentic Application Template](https://github.com/datarobot-community/datarobot-agent-application){ target=_blank }, the deployment output includes an MCP server endpoint. Use the URL shown there for your client.

Endpoint reference¶

Cursor¶

Cursor can connect to MCP servers over HTTP. Use a url entry pointing at your MCP server’s HTTP-capable endpoint.

Configuration file location¶

• Project-specific: <project-root>/.cursor/mcp.json
• Global: ~/.cursor/mcp.json

Sample configuration¶

Local MCP server (DataRobot MCP Template on port 8080):

{
  "mcpServers": {
    "datarobot-mcp": {
      "url": "http://localhost:8080/mcp",
      "headers": {
        "Authorization": "Bearer <DR_API_KEY>",
        "x-datarobot-api-token": "<DR_API_KEY>"
      }
    }
  }
} 

Local MCP server (DataRobot Agentic Application on port 9000):

{
  "mcpServers": {
    "datarobot-mcp": {
      "url": "http://localhost:9000/mcp",
      "headers": {
        "Authorization": "Bearer <DR_API_KEY>",
        "x-datarobot-api-token": "<DR_API_KEY>"
      }
    }
  }
} 

Deployed MCP server (replace with your endpoint and, if required, add auth as supported by your server):

{
  "mcpServers": {
    "datarobot-mcp": {
      "url": "https://{DATAROBOT_URL}/api/v2/deployments/{DEPLOYMENT_ID}/directAccess/mcp",
      "headers": {
        "Authorization": "Bearer <DR_API_KEY>",
        "x-datarobot-api-token": "<DR_API_KEY>"
      }
    }
  }
} 

Apply and verify¶

To confirm connectivity:

1. Save mcp.json in the correct location.
2. Restart Cursor (or reload the window).
3. In Chat or Composer, ask the AI to list or use tools from the DataRobot MCP server.

Claude Desktop¶

Claude Desktop can connect to remote MCP servers over HTTP. Configure the MCP server in claude_desktop_config.json.

Configuration file location¶

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

Sample configuration¶

Local MCP server (DataRobot MCP Template on port 8080):

{
  "mcpServers": {
    "datarobot-mcp": {
      "url": "http://localhost:8080/mcp",
      "headers": {
        "Authorization": "Bearer <DR_API_KEY>",
        "x-datarobot-api-token": "<DR_API_KEY>"
      }
    }
  }
} 

Local MCP server (DataRobot Agentic Application on port 9000):

{
  "mcpServers": {
    "datarobot-mcp": {
      "url": "http://localhost:9000/mcp",
      "headers": {
        "Authorization": "Bearer <DR_API_KEY>",
        "x-datarobot-api-token": "<DR_API_KEY>"
      }
    }
  }
} 

Deployed MCP server (replace with your endpoint and, if required, add auth as supported by your server):

{
  "mcpServers": {
    "datarobot-mcp": {
      "url": "https://{DATAROBOT_URL}/api/v2/deployments/{DEPLOYMENT_ID}/directAccess/mcp",
      "headers": {
        "Authorization": "Bearer <DR_API_KEY>",
        "x-datarobot-api-token": "<DR_API_KEY>"
      }
    }
  }
} 

If your deployment requires authentication, add the appropriate headers or token mechanism as supported by Claude Desktop and your MCP server (e.g., environment variables or config fields; check Claude Desktop documentation and your server docs).

Apply and verify¶

To confirm the connection:

1. Save claude_desktop_config.json in the correct path.
2. Restart Claude Desktop.
3. In a new conversation, ask Claude to use tools or resources from the DataRobot MCP server.

VS Code¶

VS Code (with GitHub Copilot) includes built-in MCP client support. You can connect to MCP servers over HTTP by configuring the MCP server in Copilot settings or in your VS Code settings.

Configuration file location¶

For the exact configuration keys and file locations, see Use MCP servers in VS Code. User settings are configured via Settings → Copilot → MCP servers, or by adding MCP server entries to your user or workspace settings.json.

Sample configuration¶

Local MCP server (DataRobot MCP Template on port 8080):

{
  "mcpServers": {
    "datarobot-mcp": {
      "url": "http://localhost:8080/mcp",
      "headers": {
        "Authorization": "Bearer <DR_API_KEY>",
        "x-datarobot-api-token": "<DR_API_KEY>"
      }
    }
  }
} 

Local MCP server (DataRobot Agentic Application on port 9000):

{
  "mcpServers": {
    "datarobot-mcp": {
      "url": "http://localhost:9000/mcp",
      "headers": {
        "Authorization": "Bearer <DR_API_KEY>",
        "x-datarobot-api-token": "<DR_API_KEY>"
      }
    }
  }
} 

Deployed MCP server (replace with your endpoint and, if required, add auth as supported by your server):

{
  "mcpServers": {
    "datarobot-mcp": {
      "url": "https://{DATAROBOT_URL}/api/v2/deployments/{DEPLOYMENT_ID}/directAccess/mcp",
      "headers": {
        "Authorization": "Bearer <DR_API_KEY>",
        "x-datarobot-api-token": "<DR_API_KEY>"
      }
    }
  }
} 

If your deployed server requires a token, configure authentication using HTTP headers or the mechanism supported by VS Code Copilot and your MCP server. Avoid passing tokens in URLs or query parameters to reduce the risk of credential leakage; see Use MCP servers in VS Code and your server docs for the exact configuration.

Apply and verify¶

1. Save the MCP server configuration in the correct location (Settings → Copilot → MCP servers or settings.json).
2. Reload VS Code or the window if required.
3. In Copilot Chat, ask the AI to list or use tools from the DataRobot MCP server to confirm connectivity.

トラブルシューティング¶

Client cannot connect to MCP server¶

Symptoms: The IDE or Claude reports that the MCP server is unavailable, or tools do not appear.

Solutions:

1. Confirm the MCP server is running:
2. Local: run curl -i http://localhost:9000/ or curl -i http://localhost:8080/ (adjust the port to match your local MCP server setup). A successful response indicates the server is up.
3. Deployed: run curl -i <your-mcp-endpoint-url> using the exact URL from your deployment output. If the server requires authentication, you may need to pass a bearer token or other headers; see your deployment documentation. A successful response indicates the server is up.
4. Check URL and path: Use the exact base URL and path (e.g., /mcp) required by your client and server.
5. Confirm firewall and network access: For deployed servers, ensure your network allows outbound HTTPS to the DataRobot host.

Tools do not appear in the client¶

Symptoms: Connection seems OK but the client does not list MCP tools.

Solutions:

1. Restart the client (Cursor, Claude Desktop, or VS Code) after changing the MCP config.
2. Check client and MCP server logs for errors (e.g., Cursor: Output → MCP Logs; Claude: ~/Library/Logs/Claude/). A successful connection will show MCP server logs with tool registration and availability information.

Authentication errors¶

Symptoms: Requests to the deployed MCP server return 401 or similar.

Solutions:

1. Confirm the deployed server’s auth requirements (e.g., bearer token).
2. Ensure the client is configured with the correct token or credentials (environment variables or extension settings).
3. For DataRobot deployments, ensure DATAROBOT_API_TOKEN (or the equivalent used by the server) is valid and has access to the deployment.

その他のリソース¶

• Integrate tools using an MCP server — Use an MCP server from a DataRobot agentic workflow (e.g., LangGraph agent).
• DataRobot MCP Template — Build and deploy standalone MCP servers with DataRobot integration.
• DataRobot MCP Template — Configure your MCP client — Client setup details from the template repo.
• DataRobot Agentic Application Template — Full agentic application including an MCP server.
• Model Context Protocol — Official MCP specification.