Looking to make public data access easier for the AI developer ecosystem, Google has released the Data Commons Model Context Protocol (MCP) Server, an MCP server that provides a standardized way for AI agents to consume Data Commons data sets natively.

With the Data Commons MCP server, announced September 24, Data Commons data sets become instantly available for AI developers and data scientists, with no need for complex API interactions or custom code, Google said. The MCP server enables agents to handle a full range of data-driven queries from initial discovery to generative reports. The Data Commons MCP Server also advances the larger ambition of Data Commons to enable the use of real-world statistical data to reduce large language model hallucinations, the company added.

Data Commons is an open-source initiative from Google that aims to make publicly available data from around the world more accessible and useful. The Data Commons data sources are organized by categories such as agriculture, crime, demographics, education, and health and made publicly available on Google Cloud.

Developers can try the Data Commons MCP Server via the Gemini CLI. Google said the server fits naturally within Google Cloud Platform’s agent development workflows, such as the Agent Development Kit (ADK) and clients including Gemini CLI, and can be easily integrated with any other agentic workflow or platform.