Configuring GitHub Copilot in Visual Studio Code

Register watsonx.data intelligence MCP server in the GitHub Copilot in Visual Studio Code configuration to complete tasks across data governance and catalog, data quality, data lineage, and Data Product Hub with the AI agent.

For GitHub Copilot in Visual Studio Code, you can connect either by creating a mcp.json workspace configuration that points to the watsonx.data intelligence server or by using using the VS Code MCP extension.

Required configuration information

For managed MCP

  • Authentication: API key; configure the client to send your watsonx platform API key on each request. For more information, see Generating API keys and Available APIs.
  • Server URL: The service endpoint is based on your IBM Software Hub deployment URL ({cpd_cluster_host}). Example: https://{cpd_cluster_host}/semantic_agents/public/v1/mcp_server/mcp/. For more information, see Service endpoint in the API documentation.
  • Transport: http

Connecting by editing the mcp.json file

  1. Create or edit .vscode/mcp.json.

  2. Add the following configuration to the file.
    Replace placeholder values with your credentials.

    {
  "servers": {
    "wxdi-mcp-server": {
      "url": "<url_to_mcp_server>",
      "type": "http",
      "headers": {
        "x-api-key": "your api key for cpd env",
        "username": "<user name from cpd env>"
      }
    }
  }
}

  3. Save the file.

Connecting by using the VS Code MCP extension

  1. Ensure that you have the VS Copilot MCP extension.

  2. Press Ctrl+Shift+P.

  3. Run MCP: Add Server….

  4. Add the following configuration to the file.
    Replace placeholder values with your credentials.

    {
  "servers": {
    "wxdi-mcp-server": {
      "url": "<url_to_mcp_server>",
      "type": "http",
      "headers": {
        "x-api-key": "your api key for cpd env",
        "username": "<user name from cpd env>"
      }
    }
  }
}

  5. Save the file.

Next steps

Learn more