PRODUCTIVITY · RANK #3 OF 33
Excalidraw is Sharp to agents.
Discry independently scored how well an AI agent can discover and understand the Excalidraw API from what’s public — measuring discovery and comprehension separately, not a single blended number.
Familiarity 20% · what a model knew before reading the docs
Discovery
55 / 100OpenAPI specfound at https://excalidraw.com/openapi.json but invalid: unparseablePartial
llms.txtmissing headings, links, or descriptionsPartial
llms-full.txt20 tokensPass
AGENTS.mdnot found in repoFail
.well-known/mcp.jsonpresent but malformedPartial
MCP registrysmithery match for "excalidraw"Pass
robots.txt AI directivesparsed AI-bot rulesPass
Sitemappresent, no docs pages detectedPartial
Comprehension
98 / 100Factual recall1/2 passed
Request construction1/2 passed
Absence honesty1/1 passed
Where agents fail
Produce the exact HTTP request to list this account's existing items. Output the method, path, required headers, and body. — 3/3 runs failed
What format does this API use to express recurring items (e.g. RRULE, cron expression, custom object)? — 3/3 runs failed
See your own Discry result.
Drop your API docs URL. See what an agent sees — in 60 seconds, free.