COMMUNICATION · RANK #21 OF 33
Knock is Legible to agents.
Discry independently scored how well an AI agent can discover and understand the Knock API from what’s public — measuring discovery and comprehension separately, not a single blended number.
Familiarity 64% · what a model knew before reading the docs
Discovery
34 / 100OpenAPI specno publicly accessible spec foundFail
llms.txtoversized (>50KB)Partial
llms-full.txt600189 tokensPass
AGENTS.mdnot found in repoFail
.well-known/mcp.jsonnot presentFail
MCP registrynot found in probed registriesFail
robots.txt AI directivesparsed AI-bot rulesPass
Sitemappresent, no docs pages detectedPartial
Comprehension
72 / 100Factual recall1/2 passed
Request construction1/1 passed
Absence honesty1/1 passed
Where agents fail
What are the possible delivery status values this API reports for a sent message? — 3/3 runs failed
See your own Discry result.
Drop your API docs URL. See what an agent sees — in 60 seconds, free.