Google Expands AI Agent Access With MCP Support for UN Data Commons and Google Home
aiinsider ·
Google announced two initiatives to expand how AI agents access and use real-world data, adding Model Context Protocol (MCP) support to the UN System Data Commons and the Google Home ecosystem. Developed with Google, the UN System Data Commons uses Google’s open-source Data Commons platform to let users query UN statistics in natural language and connect AI systems directly through MCP. An unpublished UNICEF study cited in the announcement found that GPT-4o, Claude, and Gemini averaged just 21.2% accuracy when answering questions about global development indicators. Google.org contributed $2 million to the platform’s infrastructure, which traces statistics to their original sources, although Google said human review is still needed before publishing AI-generated conclusions. Google also opened early access to an MCP server for Google Home, allowing agents such as Claude, ChatGPT, and Google Antigravity to control connected devices, review camera summaries, and create custom dashboards using natural language. The Google Home feature supports Nest and Matter-compatible devices, initially targets Google Home Premium Advanced subscribers in the United States, and requires users to configure a Google Cloud project before connecting an AI agent.
aiinsider