We are excited to announce the public release of the Data Commons Model Context Protocol (MCP) Server. The MCP Server provides a standardized way for AI agents to consume Data Commons data natively. Developers can easily write and deploy AI agents and applications that deliver trustable, sourced Data Commons information back to the end user. Analysts and data scientists can use simple, natural language to get fast answers, without needing to learn or directly interact with complex underlying APIs. Here are a few examples of the full range of high-level data queries:
- Exploratory: “What health data do you have for Africa?”
- Analytical: “Compare the life expectancy, economic inequality, and GDP growth for BRICS nations.”
- Generative: “Generate a concise report on income vs diabetes in US counties.”
To learn more about the immediate benefits and use cases of the Data Commons MCP Server, see the Google for Developers blog.
Ready to try?
The server is freely available as a PyPi package. It returns data from datacommons.org by default or can be configured to run against a Custom Data Commons instance.
You can use it with your favorite MCP client or get started right away with Gemini CLI.
In addition, as part of this launch, we have provided a Google ADK sample agent in our Github repository as well as a Colab notebook that shows you how to develop your own Python agent step by step.
For complete documentation, see our User Guide.