SI Readiness by MCP-Tool
llms.txt source file
Is there a curated file that tells an agent what this site is and where to look?
Why it matters
A crawl gives an agent everything; llms.txt gives it the part you would point at yourself. It is cheap to publish and it is the only place where you control the summary rather than hoping one is inferred.
How to fix it
Publish /llms.txt with a one-paragraph description, then linked lists of your canonical pages grouped by purpose. Note that it is a convention, not a standard, and Google Search ignores it.
# Acme Espresso > Acme sells espresso machines and grinders, with compatibility data for every > portafilter and basket we stock. ## Canonical pages - [Machines](https://example.com/machines) - [Grinders](https://example.com/grinders) - [Compatibility guide](https://example.com/compatibility)