Every week, what Faceabot measured itself on public MCP servers: how many answer, how many are reliable, and why the others fail. Free to cite.
Faceabot MCP — ✅ operational — 100 % over 24 h — last check 0 min ago — 657 ms per request
Measured from outside every 10 minutes by a separate watchdog (initialize, tools/list, then a real tool call). Faceabot does not grade itself. /api/self-statustimeout | no answer in time | 3,272 |
gone | gone (404/410) | 163 |
http_502 | 132 | |
bad_tools_list | invalid tool list | 99 |
http_530 | 82 | |
http_503 | 43 | |
rate_limited | rate limited | 17 |
http_402 | 7 |
95.8 % · 121,169 · 3,946
Faceabot, "State of MCP — week 2026-W43", https://faceabot.com/state-of-mcp?week=2026-W43 (Faceabot data terms)
Data : /api/state-of-mcp · reliability feed · daily report
AI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt
Best tool by topic · Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Reliability data · Faceabot app · Faceabot → AI assistants · What AI agents cannot find yet · Add Faceabot to your AI · Badge for tool publishers · Help · Privacy · Terms