Supabase · Infrastructure◎ discry
Murky
Agents misread these docs often
DISCOVERY52.6
COMPREHENSION55.5
Advanced-model required#34 of 73 Infrastructure APIs · 55th percentile
INFRASTRUCTURE · RANK #34 OF 73

Supabase is Murky to agents.

Discry independently scored how well an AI agent can discover and understand the Supabase API from what’s public — measuring discovery and comprehension separately, not a single blended number.

Familiarity 64% · what a model knew before reading the docs

Discovery

53 / 100
OpenAPI specno publicly accessible spec foundFail
llms.txt31 described linksPass
llms-full.txt1675582 tokensPass
AGENTS.mdnot found in repoFail
.well-known/mcp.jsonnot presentFail
MCP registrysmithery match for "supabase"Pass
robots.txt AI directivesparsed AI-bot rulesPass
Sitemapincludes docs pagesPass

Comprehension

56 / 100
Request construction0/2 passed
Absence honesty1/1 passed

Where agents fail

Produce the exact HTTP request to list this account's existing resources. Output the method, path, required headers, and body. 2/3 runs failed

Produce the exact HTTP request to provision a new resource named build-runner-01. Output the method, path, required headers, and body. 2/3 runs failed

See your own Discry result.

Drop your API docs URL. See what an agent sees — in 60 seconds, free.

Discry your API — free