CGU's MCP Bridge for Brazil's Open Data — Testing Whether LLMs Can Be Trusted with Government Datasets

The Controladoria-Geral da União (CGU), Brazil's federal body responsible for transparency and anti-corruption oversight, partnered with the Open Knowledge Foundation (OKFN) and Uruguay's e-government agency AGESIC to test whether large language models can be trusted to answer citizens' questions about official open data.
Using the Model Context Protocol (MCP), the team connected an LLM directly to CKAN, the open-source software that powers most of the world's public data portals, including Brazil's federal transparency portal. In Brazil, the pilot targeted one of the portal's most-requested datasets: congressional parliamentary amendments. In a parallel pilot, Uruguay connected the same architecture to its National Energy Balance dataset, covering energy imports, generation and installed capacity.
The technical connection worked; the harder problem was trust. Published in June 2026, the project's own write-up reports that answer quality depended less on the pipeline than on how well the underlying data was described — units, field definitions, valid assumptions. In testing on the Uruguayan dataset, the model fabricated 'climate factors' as part of its explanation even though no climate data existed anywhere in the source — a concrete, publicly documented hallucination that the team used to argue for mandatory domain-expert review of dataset descriptions before any citizen-facing deployment.
As of publication the work remains a two-dataset prototype; the next planned phase is user testing with real-world citizen questions rather than production rollout. The team describes the parallel Brazil/Uruguay design as a deliberate attempt to build a reproducible blueprint that any government running a CKAN-based open data portal could adopt.

Read the full analysis: https://blog.okfn.org/2026/06/10/mcp-for-open-data-portals-trust-depends-on-understanding-the-data/