MCP server
Autopia
By maydaytrey
Verified, reproduced behavior of public HTTP APIs: spec gaps, errors, pagination, auth.
Listed on
First seen 12 Oct 2026. One server, whatever directories list it: each directory listing keeps its own page and history.
1
Directories
Collected by InvokeRank
9
Tools
From an anonymous probe
-
ToolBench grade
Not graded by Arcade
-
GitHub stars
No repository data
Tools
| Tool | Description | Behaviour |
|---|---|---|
| get_divergences | Where the live API CONTRADICTS its own OpenAPI spec: documented limits not enforced, types not validated, required params not required, enums that accept other values. Read before trusting a spec-generated client or SDK for this API. Compact evidence; verbose=true adds response previews. | Not declared |
| get_request_status | Status of a target request: pending | running | done | failed, with the run id and summary once processed. | Not declared |
| get_tool_docs | READ THIS BEFORE YOUR FIRST CALL to an API the compendium covers. Pass the host or URL you are about to call (api.github.com, https://registry.npmjs.org/-/v1/search) or the tool name. Returns a Markdown behavior sheet built only from verified claims: where the API contradicts its spec first, then sibling differences, undocumented rules, and per-endpoint behavior (error shapes, pagination, validation, auth). Each line cites the trial ids that back it. One read; no need to repeat it in the same session. brief=true returns only spec divergences, undocumented rules, and auth / pagination / error behavior (about a third of the size). Pass the request path (or a full URL as tool) to get ONLY the endpoint you are about to call plus a one-line index of the others; descend to another by passing its path. | Not declared |
| get_tool_knowledge | Every VERIFIED claim about an API as structured records (latest version by default), paginated, spec divergences flagged, each with compact evidence (trial id, probe, status, request line). Use when you need to filter by kind or process claims programmatically; for the one-read summary before calling the API use get_tool_docs. verbose=true adds response previews. | Not declared |
| get_version_diff | What changed in verified BEHAVIOR between two spec versions of an API (changed / added / removed claims), as opposed to what changed in the spec text. Version ids come from list_versions. | Not declared |
| list_tools | Which APIs the compendium covers, each with the HOSTS its trials hit (match the URL you are about to call), trust tier, version count and verified-claim / divergence counts. Call once per session; then get_tool_docs for the host you are about to call. | Not declared |
| list_versions | Spec versions of one API, newest first, each fingerprinted by its spec hash. Use with get_version_diff when a spec changed and you want to know what changed in BEHAVIOR. | Not declared |
| request_target | The API you are about to call is NOT covered (not in list_tools)? Ask the compendium to test it. Pass a target object: { name, spec_url (OpenAPI 3 document), category?, include_paths?, baseline? (valid values for required params per path), optional_values?, server? }. Scope: public read-only APIs with no credentials (no headers accepted). The request is validated now (spec fetched and parsed, battery planned) and processed rules-only on the worker's next pass; use get_request_status with the returned id. Requires a per-user key. Quota: 3 requests per key per day. | Not declared |
| search_claims | Call this when an API call FAILED or behaved unexpectedly: an unexpected 4xx/5xx, a parameter that seems ignored, an odd page, wrong filter results. Full-text search over verified claims with the host and the symptom, e.g. "github per_page 500", "npm search size 0", "is latitude required on /v1/forecast". Optionally restrict to one API (name, host or URL). Compact evidence unless verbose=true. | Not declared |
| Directory | Listing | Tier | First seen |
|---|---|---|---|
| Official MCP Registry | Autopia | - | 12 Oct 2026 |