alt

Traceable AI Answers for Public Data

As artificial intelligence increasingly becomes a primary interface for accessing information, ensuring that AI-generated responses are accurate, transparent, and grounded in trusted sources is increasingly important. Public institutions publishing open data face a new challenge: how to ensure that AI tools referencing their datasets provide verifiable and trustworthy answers.

We are building a technical bridge (using the Model Context Protocol) that connects AI directly to official data portals like CKAN, so that AI-generated responses can be traced back to their original datasets. This reinforces trust in public institutions, helps fight misinformation, makes open data more accessible for citizens and ensures that research or journalism based on that data is grounded in fact.

Key outputs

  • An open-source implementation of a Model Context Protocol (MCP) server specifically for CKAN, the software that powers many of the world’s public data portals.
  • A system that allows AI tools to pull information directly from official datasets, providing users with a link back to the original source.
  • A simplified way for citizens, researchers, and journalists to query complex public databases using natural language without losing accuracy.
  • Installation and replication documentation to serve as a replicable model for other federal agencies and the global CKAN community.
 

Who is this for:

  • Government data portal owners
  • Civic tech developers
  • Open data advocates
  • Journalists and researchers

 


 

Partners

This project is a collaborative initiative grounded in real-world challenges. Two pilot programmes are taking place in 2026 under the umbrella of the Digital Public Goods Alliance (DPGA) in partnership with national governments to become a reproducible and scalable reference of responsible and transparent AI integration with open data infrastructure.


 

Follow our progress, from research notes to community stories:

7 April 2026
'An Honest Reflection on the Integration of LLMs into Open Data Portals', by Patricio Del Boca 7 April 2026
25 March 2026
[Recording] Technical community consultation on MCPs and LLMs 25 March 2026
11 March 2026
Roundtable: 'CKAN at 20 and the Future of Open Data' 11 March 2026
16 December 2025
Announcement of Strategic Funding to Enhance Multilingual, Sector-specific AI Literacy and Develop Trustworthy AI for Open Data 16 December 2025

 

If you have any questions or want any additional information about the Open Data Editor, you can contact us at info@okfn.org.

 


 

CKAN is the world’s leading open source data management system. Created at OKFN two decades ago and a recognised digital public good (DPG) since 2023, CKAN is the backbone of open data infrastructure on every continent — powering national governments, intergovernmental bodies, and research institutions. 

🎉 We are celebrating 20 years of CKAN with various activities throughout 2026.


 

This project has been made possible thanks to the generous support of the Patrick J. McGovern Foundation (PJMF). We are grateful for our ongoing partnership in promoting digital literacy and investing in AI for the public good. 

Learn more about its funding programmes here.

 

colors
Let's build together a world where all knowledge is
accessible to everyone
Get in touch

Don't miss a thing

Stay on top of what's happening in the #OpenMovement around the world. (We will never spam you!)