AUTH · RANK #13 OF 21
Clerk is Murky to agents.
Discry independently scored how well an AI agent can discover and understand the Clerk API from what’s public — measuring discovery and comprehension separately, not a single blended number.
Familiarity 56% · what a model knew before reading the docs
Discovery
53 / 100OpenAPI specno publicly accessible spec foundFail
llms.txt85 described linksPass
llms-full.txt192 tokensPass
AGENTS.mdnot found in repoFail
.well-known/mcp.jsonnot presentFail
MCP registrysmithery match for "clerk"Pass
robots.txt AI directivesparsed AI-bot rulesPass
Sitemapincludes docs pagesPass
Comprehension
54 / 100Factual recall0/2 passed
Absence honesty1/1 passed
Where agents fail
What HTTP header (exact header name) must carry the API credential on requests to this API? — 3/3 runs failed
Which multi-factor authentication factor types does this API support? — 3/3 runs failed
See your own Discry result.
Drop your API docs URL. See what an agent sees — in 60 seconds, free.