ANALYTICS · RANK #14 OF 36
LunarCrush is Legible to agents.
Discry independently scored how well an AI agent can discover and understand the LunarCrush API from what’s public — measuring discovery and comprehension separately, not a single blended number.
Familiarity 67% · what a model knew before reading the docs
Discovery
63 / 100OpenAPI specfound at https://lunarcrush.com/openapi.json but invalid: unparseablePartial
llms.txt22 described linksPass
llms-full.txt1235 tokensPass
AGENTS.mdnot found in repoFail
.well-known/mcp.jsonpresent but malformedPartial
MCP registrysmithery match for "lunarcrush"Pass
robots.txt AI directivesparsed AI-bot rulesPass
Sitemappresent, no docs pages detectedPartial
Comprehension
66 / 100Factual recall1/2 passed
Absence honesty1/1 passed
Where agents fail
What field name does this API use for the timestamp on an event or data point (exact field name)? — 3/3 runs failed
See your own Discry result.
Drop your API docs URL. See what an agent sees — in 60 seconds, free.