Eclipse Benchkit runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 27 Oct 2026.
Free vendor self-bench SDK — Assay scorecard format + verifier spot-check sampling.
Today is the operative word: we check Eclipse Benchkit every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Eval-expiry clock over fixture Benchkit scorecards + fixture drift evidence; local stdio MCP only.
The HubSpot wrap: the vendor's server, under policy — classified tools, approval gates, masking
MCP server for cross-vendor API/SDK deprecation and breaking-change tracking
Scan any website or MCP server for agent readiness: 0-100 score, a fix per failing check. Free.
Email validation for AI assistants: verdict, risk score, evidence. Free: 100 checks a month.
Check whether a real-world fact can be verified before an agent acts on it. Free, no auth.
Trust layer for the x402 economy - check any service before you pay. Scores, discovery, routing.
Trust metadata for AI agents — check files before building on them, stamp verified work.
Answers built from our own checks of this server.