What we tested
Probed live on 23 Aug 2026 against rubric v1. 4 of 5 checks passed.
PROBE-VERIFIEDtier 2 of 3
✓Markdown negotiationAccept: text/markdown
✓Markdown twin at a predictable URL/page.md
✓llms.txt/llms.txt
—API catalogRFC 9727
✓MCP server answers/.well-known/mcp/server-card.json → tools/list
What its MCP server offers
We connected, ran tools/list, and recorded what came back on 23 Aug 2026. 3 tools, served from fastmcp.main-kill-isr.mintlify.me — the standard set for sites on mintlify.
search_fast_mcpquery_docs_filesystem_fast_mcpsubmit_feedback
What an agent could do here
Read from the page’s own content, with the wording each was drawn from. Inference is kept separate from tested facts — an agent completing the action is tier 3.
UNVERIFIED
read“Fetch the complete documentation index at: https://gofastmcp.com/llms.txt”https://gofastmcp.com/llms.txt
Context
8 sites in the index share the category software framework, of which 1 are transactional.
How we grade
Three tiers. Every listing shows which one it has reached, and when. The rubric.
tier 1Declared
The site says agents are welcome in its robots.txt. A permission, not a capability.
tier 2Probe-verified
We fetched the site and tested each signal ourselves. Dated, repeatable, re-checked on a schedule.
tier 3Behaviourally verified
An agent completed the action end to end — booked, bought, submitted — and it worked.
Own this site?
1 check did not pass when we last looked: API catalog. Each is a small, specific fix; the rubric says exactly what we look for.
Behavioural verification — an agent completing your booking, purchase or contact flow end to end, with the date published here — opens to a small founding cohort first. Leave an email to be in it.
Related verified sites
Confect 🧁Confect integrates Effect with Convex for type-safe full-stack app development using schem
software framework FastMCPFastMCP is a framework for building Model Context Protocol servers, clients, and interacti
software framework mcp-agentDocumentation site for mcp-agent, a framework to build agents using Model Context Protocol
software framework PhidataPhidata is a framework for building multi-modal agents and workflows to automate intellige
software framework prachtDocumentation site for the Preact-based Pracht framework featuring explicit routing and mu
software framework Framework7Framework7 is a free and open source framework for building iOS, Android, desktop, and web
software framework Mantle by AlleyMantle is a Laravel-inspired framework for building large websites and applications with W
software framework Aptos DocumentationAptos Developer Documentation provides guides, SDKs, and tools to build Web3 applications
blockchain developer documentation Record generated from a live database query. Method: about the index.