Agents Index

Autopia

Online

Verified, reproduced behavior of public HTTP APIs: spec gaps, errors, pagination, auth.

Visit publisherConnectJSON

What it can do: 9 tools

  • list_tools read-onlyThe APIs the compendium covers: each with the hosts its trials hit, trust tier, version count, and counts of verified claims and spec divergences.
  • list_versions read-onlyThe spec versions recorded for one API, newest first, each fingerprinted by its spec hash. The ids identify versions for get_version_diff.
  • get_tool_knowledge read-onlyEvery verified claim about an API as structured records (latest version by default): paginated, filterable by kind, spec divergences flagged, each with compact evidence (trial id, probe, status, request line). verbose=tr
  • get_divergences read-onlyWhere the live API contradicts its own OpenAPI spec: documented limits not enforced, types not validated, required parameters not required, enums accepting other values. Compact evidence; verbose=true adds response previ
  • search_claims read-onlyFull-text search over verified claims by host and symptom, e.g. "github per_page 500", "npm search size 0", "is latitude required on /v1/forecast": the lookup for an unexpected 4xx/5xx, a parameter that seems ignored, an
  • get_tool_docs read-onlyThe verified behavior sheet for an API: Markdown built only from verified claims, with spec contradictions first, then sibling differences, undocumented rules, and per-endpoint behavior (error shapes, pagination, validat
  • get_version_diff read-onlyWhat changed in verified behavior between two spec versions of an API (changed, added and removed claims), as opposed to what changed in the spec text.
  • request_targetQueues a public, read-only, credential-free API for probing, from a target object { name, spec_url (OpenAPI 3 document), category?, include_paths?, baseline? (valid values for required params per path), optional_values?,
  • get_request_status read-onlyStatus of a target request (pending, running, done or failed), with the run id and summary once processed.

Connect it

Claude Code
claude mcp add --transport http autopia https://autopia-mcp.onrender.com/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://autopia-mcp.onrender.com/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "autopia": {
      "url": "https://autopia-mcp.onrender.com/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "autopia": {
      "type": "http",
      "url": "https://autopia-mcp.onrender.com/mcp"
    }
  }
}

Questions

What does Autopia do?

Verified, reproduced behavior of public HTTP APIs: spec gaps, errors, pagination, auth. It exposes 9 tools to AI assistants.

What tools does Autopia provide?

9 tools, including list_tools, list_versions, get_tool_knowledge, get_divergences, search_claims, get_tool_docs, get_version_diff, request_target, get_request_status.

How do I connect Autopia to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://autopia-mcp.onrender.com/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does Autopia require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is Autopia online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes Autopia?

@MaydayTrey on GitHub. The official MCP Registry verified that the publisher controls this GitHub account before accepting the listing.

Similar in Productivity & Docs