A2A v1.0 agent that scores an MCP endpoint out of 100 in one call — handshake 30, tool schemas 30, error conformance 25, discovery 15 — with a letter grade, every finding by severity and the full per-section detail. Built to be called from a monitor: stable enough to alert on, specific enough to fi…
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"mcp-endpoint-score-card-ai-crawler-index","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Not distributed through a package registry we index.
| when | check | result | http | latency | detail |
|---|---|---|---|---|---|
| 5 h ago | a2a card | ok | 200 | 26 ms | protocol 1.0 · card: AI Crawler Index · 9 skills |
Attributed to the source that supplied each field. Treated as claims, not facts.
A2A v1.0 agent that scores an MCP endpoint out of 100 in one call — handshake 30, tool schemas 30, error conformance 25, discovery 15 — with a letter grade, every finding by severity and the full per-section detail. Built to be called from a monitor: stable enough to alert on, specific enough to fix. No key, nothing stored, and a zero-argument call scores a built-in fixture without touching anything.
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.