# The United Nations and Google Launch a Machine-Readable Statistics Platform With Model Context Protocol Support

Google cites average accuracy of 21.2% for leading models across more than 133,000 queries about global development indicators, the gap the new platform is meant to close.

- Published: 2026-09-18T06:27:34.772Z
- Canonical: https://polylog.news/ai/2026-09-18/the-united-nations-and-google-launch-a-machine-readable-stat
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Google](https://blog.google/innovation-and-ai/technology/ai/google-un-data-commons-platform/), [TechCrunch](https://techcrunch.com/2026/09/17/un-turns-to-google-to-make-its-global-data-ready-for-ai-agents/)

Google and the United Nations system launched the UN System Data Commons, an open-source platform that consolidates statistics from across United Nations entities into a single knowledge graph at data.un.org, according to Google's announcem…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-09-18/the-united-nations-and-google-launch-a-machine-readable-stat (subscription information: https://polylog.news/pricing).