AI · RANK #16 OF 51
Anthropic is Clear to agents.
Discry independently scored how well an AI agent can discover and understand the Anthropic API from what’s public — measuring discovery and comprehension separately, not a single blended number.
Familiarity 93% · what a model knew before reading the docs
Discovery
47 / 100OpenAPI specno publicly accessible spec foundFail
llms.txt33 described linksPass
llms-full.txt6307597 tokensPass
AGENTS.mdnot found in repoFail
.well-known/mcp.jsonnot presentFail
MCP registrynot found in probed registriesFail
robots.txt AI directivesparsed AI-bot rulesPass
Sitemapincludes docs pagesPass
Comprehension
98 / 100Factual recall2/2 passed
Request construction2/2 passed
Absence honesty1/1 passed
See your own Discry result.
Drop your API docs URL. See what an agent sees — in 60 seconds, free.