Mri Mcp
Which source domains AI answer engines cite, by buyer category and question shape.
- Transport
- Not stated
- Package
- —
- Registry id
- ai.machinerelations/mri
No install snippet on purpose. A working MCP config is a command, its arguments and an environment block — the last two are where API keys live, so this catalogue never stores them and cannot publish them. Follow the link above for the authors' own instructions.
The Machine Relations Index is a neutral public benchmark for how AI answer engines cite sources. It reports citation rates by category and question type once minimum sample thresholds are met. The benchmark covers 29,181 domains, 180,895 source events, 23,344 answer runs, and 115 out of 151 measurable segments validated.
It observes six answer engines: Perplexity, ChatGPT, Gemini, Claude, Google AI Mode, and Google AI Overviews. The measurement window for the current release is 2026-05-10 to 2026-10-11. A stratum publishes a citation rate only after it clears the evidence floor of at least 10 observed runs across at least 7 distinct dates.
Validated source segments currently cover 76.2% of the measurable benchmark.
Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.