PAYMENTS · RANK #26 OF 34
Wise is Murky to agents.
Discry independently scored how well an AI agent can discover and understand the Wise API from what’s public — measuring discovery and comprehension separately, not a single blended number.
Familiarity 46% · what a model knew before reading the docs
Discovery
21 / 100OpenAPI specno publicly accessible spec foundFail
llms.txtnot found (a probe was bot-blocked: HTTP 403)Fail
llms-full.txtnot presentFail
AGENTS.mdno github org knownFail
.well-known/mcp.jsonnot presentFail
MCP registrysmithery match for "wise"Pass
robots.txt AI directivesparsed AI-bot rulesPass
Sitemapnot presentFail
Comprehension
54 / 100Factual recall1/1 passed
Request construction0/1 passed
Absence honesty1/1 passed
Where agents fail
Produce the exact HTTP request to create a new customer with email jane@acme.test. 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.