evidoria

← Back to browse

Good practice Imported

AGESIC and OKFN's Traceable AI for Uruguay's Open Data Catalogue

Uruguay · Montevideo · See the Uruguay profile · See the Montevideo profile

Evidence: Descriptive / self-reported Top 83% 40/100 · Ask Evidence Copilot about this practice

Uruguay's AGESIC and the Open Knowledge Foundation piloted a Model Context Protocol server letting citizens ask natural-language questions of the open-data catalogue with answers traced to source datasets; launched June 2026, no usage data published yet.

AGESIC and OKFN's Traceable AI for Uruguay's Open Data Catalogue

Details

Maturity
Pilot
Promoter
AGESIC (Agencia de Gobierno Electrónico y Sociedad de la Información y del Conocimiento)
Period
2026
Keywords
open data, digital government, transparency, generative AI

Context

Uruguay's open-data catalogue (catalogodatos.gub.uy) holds thousands of government datasets, but citizens without technical skills struggle to find and interpret them, and generic AI chatbots risk answering from ungrounded or fabricated information rather than the real data.

Objectives

Let users ask natural-language questions of the open-data catalogue and receive answers traced directly to the underlying datasets, instead of free-form generated text.

Activities

AGESIC partnered with the Open Knowledge Foundation's Tech Team to prototype a Model Context Protocol (MCP) server designed to work with any CKAN-based data portal, funded by the Patrick J. McGovern Foundation and following the open, reusable model promoted by the Digital Public Goods Alliance.

Conclusions

Announced in June 2026, the project is explicitly an early pilot: OKFN's own announcement reports no usage metrics or performance figures, and it is included here as an early, transparently-designed model for verifiable AI access to public data — not yet as a proven success.

Implementation
Indicative cost
Low (< €50k)
Time to results
Short (< 1 year)
Staffing & skills
AGESIC (Agencia de Gobierno Electrónico y Sociedad de la Información y del Conocimiento), Open Knowledge Foundation Tech Team

Conditions for success

  • Funding from the Patrick J. McGovern Foundation
  • Adherence to the Digital Public Goods Alliance's open, reusable model and CKAN compatibility for portability

Commonly funded by

National / regional programmes Philanthropic / foundation funding

Indicative funding routes for practices of this type — always check each programme's current calls and eligibility rules.

Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.

Data sources

Where this practice's information was retrieved from, and when.

Attachments

Similar practices you may find useful