COMMERCE · RANK #12 OF 27
Snipcart is Murky to agents.
Discry independently scored how well an AI agent can discover and understand the Snipcart API from what’s public — measuring discovery and comprehension separately, not a single blended number.
Familiarity 60% · what a model knew before reading the docs
Discovery
26 / 100OpenAPI specno publicly accessible spec foundFail
llms.txtnot presentFail
llms-full.txtnot presentFail
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
66 / 100Factual recall2/2 passed
Request construction0/1 passed
Absence honesty1/1 passed
Where agents fail
Produce the exact HTTP request to create a new product named Canvas Tote priced at 25 USD. Output the method, path, required headers, and body. — 3/3 runs failed
See your own Discry result.
Drop your API docs URL. See what an agent sees — in 60 seconds, free.