UN opens Google-backed Data Commons for AI-queryable statistics

The United Nations on Thursday announced the UN System Data Commons with Google, replacing the UNData portal with a natural-language platform that supports the Model Context Protocol so AI systems can query official statistics directly. Twenty-six UN entities have committed, with data from nearly 20 available at launch, and the system aims to cover 80% of UN statistical datasets by 2027. Google.org provided $2 million in capacity-building funding; the instance is UN-governed and intended to be operated independently. A UNICEF working paper, not yet peer-reviewed, found six large language models averaged 21.2% accuracy on more than 133,000 development-indicator questions, with many answers unusable or inconsistent. Google demonstrated MCP-connected agents assembling dashboards from UN indicators. Prem Ramaswami of Google's Data Commons team said humans should review outputs before citing them.