Earlier this year, we announced 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. Analysts can ask high-level questions in natural language, while developers can easily create AI agents customized for their needs. 

The server provides tools that are optimized to answer queries such as:

Exploratory: “What poverty indicators for India do you have?”

Analytical: “List out the GDP per capita for all the OECD countries, rank-ordered by GDP.”

Generative: “Write a summary of the birth rates in China and India since 1970.”

When used with Gemini CLI as the client, Data Commons also allows grounding of responses from the GoogleSearch tool with authoritative data. 

Today, we are making it even easier to use Data Commons with Gemini CLI by releasing a Gemini CLI extension. The extension provides an out-of-the-box agent, with a context file that guides the model on how to query the MCP server tools. The extension simplifies installation and setup so you can get started in minutes. 

Check out https://github.com/gemini-cli-extensions/datacommons for instructions on installation and usage.