okf-ons — OKF Bundle for MCP Integration
DraftOpen Knowledge Format bundle for discovering and selecting Office for National Statistics data, updated after the Hackathon 2026-07-20 with the input from the winning team. All questions about the DEVELOPING https://github.com/onsdigital/explore-local-statistics-app should be directed to Explore.Local.Statistics@ons.gov.uk
Best for
- AI agents using the MCP protocol
What it does
- Open Knowledge Format bundle for discovering and selecting Office for National Statistics data, updated after the Hackathon 2026-07-20 with the input from the winning team.
- All questions about the DEVELOPING https://github.com/onsdigital/explore-local-statistics-app should be directed to Explore.Local.Statistics@ons.gov.uk.
How to use with AI agents
Step 1: Clone the repository
git clone https://github.com/chris-page-gov/okf-ons
cd okf-onsStep 2: Point your AI agent at the bundle directory
# Claude Code
claude /path/to/okf-ons# Cursor
cursor /path/to/okf-ons# OpenCode
opencode /path/to/okf-onsMCP: This bundle supports the Model Context Protocol. Configure your MCP client to discover and load this bundle.
Frequently Asked Questions
Is okf-ons OKF conformant?
No, okf-ons is currently marked as a draft bundle. It may not fully follow the OKF specification yet.
How do I install okf-ons?
Clone the repository and point your AI agent at the bundle directory. The agent will automatically discover and load the OKF knowledge. No additional tools or SDKs are required.
What AI agents can use okf-ons?
okf-ons works with any AI agent that supports OKF bundles, including Claude Code, Cursor, OpenCode. Just point your agent at the bundle directory.
What are alternatives to okf-ons?
Similar bundles include pi-llm-wiki, OKFy, sample-okf-llm-wiki. Browse these for alternative approaches and feature sets.