Google Makes Public Datasets More Accessible with Release of Data Commons MCP Server

  • By John K. Waters
  • 09/29/25

Google has announced the public release of its Data Commons Model Context Protocol (MCP) Server, a tool designed to make the company's extensive collection of public datasets more accessible to AI developers and data scientists.

The MCP Server provides a standardized way for AI agents to consume Data Commons datasets without requiring direct interaction with underlying APIs. According to Google software engineer Keyur Shah, the release represents "a major milestone in making all of Data Commons' vast and interconnected public datasets instantly accessible and actionable for AI developers, data scientists, and organizations worldwide."

The company said the server can support exploratory, analytical, and generative queries, ranging from broad searches for regional health data to multi-variable comparisons and report generation. Developers can integrate the tool into workflows on Google Cloud Platform, including the Agent Development Kit (ADK) and Gemini CLI, or with other agent frameworks.

As an early application, Google cited its collaboration with the ONE Campaign, a global advocacy group focused on poverty and health. Using the MCP Server, the organizations developed the ONE Data Agent, an interactive platform for health financing data. The tool enables users to search, visualize, and download large volumes of data in seconds, reducing the manual work required to combine information from disparate databases.

Google stated that the MCP Server is available through PyPI and can be utilized with Colab notebooks and the company's sample agents on GitHub.

For more information, visit the Google blog.

About the Author

John K. Waters is the editor in chief of a number of Converge360.com sites, with a focus on high-end development, AI and future tech. He's been writing about cutting-edge technologies and culture of Silicon Valley for more than two decades, and he's written more than a dozen books. He also co-scripted the documentary film Silicon Valley: A 100 Year Renaissance, which aired on PBS.  He can be reached at [email protected].

Featured

  • Hand holding a stylus over a tablet with futuristic risk management icons

    Why Universities Are Ransomware's Easy Target: Lessons from the 23% Surge

    Academic environments face heightened risk because their collaboration-driven environments are inherently open, making them more susceptible to attack, while the high-value research data they hold makes them an especially attractive target. The question is not if this data will be targeted, but whether universities can defend it swiftly enough against increasingly AI-powered threats.

  • interconnected blocks of data

    Rubrik Intros Immutable Backup for Okta Environments

    Rubrik has announced Okta Recovery, extending its identity resilience platform to Okta with immutable backups and in-place recovery, while separately detailing its integration with Okta Identity Threat Protection for automated remediation.

  • teenager’s study desk with a laptop displaying an AI symbol, surrounded by books, headphones, a notebook, and a cup of colorful pencils

    Survey: Student AI Use on the Rise

    Ninety-three percent of students across the United States have used AI at least once or twice for school-related purposes, according to the latest AI in Education report from Microsoft.

  • cybersecurity book with a shield and padlock

    NIST Proposes New Cybersecurity Guidelines for AI Systems

    The National Institute of Standards and Technology has unveiled plans to issue a new set of cybersecurity guidelines aimed at safeguarding artificial intelligence systems, citing rising concerns over risks tied to generative models, predictive analytics, and autonomous agents.