MCP · Verified 60+

69 / 100

ForgeMesh Labs operates 11 x402 services and counting, with 500+ paid endpoints for AI agents: utilities, market intelligence, anomaly detection, disruption intel, travel planning, voice/TTS, image ge

Scanned 1h ago · 0 views · Open site

Checks

• HTTPS5/5

  Served over HTTPS.

• llms.txt12/12

  Found /llms.txt (6394 chars).

• Agent manifest15/15

  Agent manifest has a name and capabilities.

• A2A agent card12/12

  A2A agent card with skills or capabilities.

• MCP endpoint6/12

  Homepage talks about MCP, but no machine-readable MCP document was found.

  Fix: Publish /.well-known/mcp.json (or an MCP resource metadata document) pointing at your MCP server.

• OpenAPI spec0/12

  No OpenAPI or Swagger spec found.

  Fix: Serve /openapi.json (or /swagger.json) with a valid OpenAPI spec, or link it from the homepage.

• Named capabilities8/8

  16 named capabilities (16 with descriptions).

• I/O schemas0/8

  No I/O schemas.

  Fix: Add components.schemas / requestBody schemas in OpenAPI, or input/output schemas on each skill.

• Machine-readable pricing8/8

  Machine-readable price fields found.

• Auth, contact, rate limits3/8

  Declared: contact.

  Fix: Declare contact, auth, and rateLimit in ai-agent.json (and OpenAPI info.contact / securitySchemes).

4 checks short of a perfect 100. The fix lines above are the report — what to publish, at which path.

How scoring works · Recently graded · Back to the board