In late 2025, we announced the Data Commons Model Context Protocol (MCP) server and the Gemini CLI extension. Both launches required that you install additional open-source Python tools and run the MCP Server package locally.

Today, to make it easier for everybody to use datacommons.org with an LLM, we are providing a hosted Data Commons MCP service in Google Cloud Platform. Now you don’t have to run your own server – you can just connect to the free service and let Google manage the rest.

Connect today!

If you’re already using the Data Commons Gemini CLI extension, you don’t need to do anything. The next time you run Gemini CLI, the extension will automatically update itself to connect to the server over the web instead of starting up a local server instance. If you haven’t used the extension before, see Use the Gemini CLI extension to get started.

If you’re using Gemini CLI without the extension, or any other agent, you’ll need to update your configuration to point to the hosted server. Along with a Data Commons API key, the snippet below is all you need. For complete details, see Use Gemini CLI.

"mcpServers": {
   "datacommons-mcp": {
      "httpUrl": "https://api.datacommons.org/mcp",
      "headers": {
        "X-API-Key": "YOUR DC API KEY"
      }
   }
}

And as always, if you’re interested in sharing your cool usage of Data Commons or have feedback, please email us at support@datacommons.org. 

Note: The hosted MCP server can only be used to query datacommons.org. If you’re running your own Custom Data Commons instance, you’ll still need to run your own MCP server. See Run MCP tools for more information.