Is crewai.com agent ready?

crewai.com is largely agent ready: it scores 74/100 (grade B) on the w2agent rubric. Weakest areas: Agent Discovery (38).

74/ 100
Grade: B

Last checked · Platform: nextjs

Scored Oct 14, 2026 · Rubric v3.0

Changed since last check

−6 points since the previous check (2026-09-16)

Regressed: Public API surface, Agent/bot auth documentation, Scoped API permissions, Content negotiation (Markdown)

Changed: Response time (fail → partial)

Category scores

Technical
91
Agent Auth
70
Agent Discovery
38
Agent Protocols
68
Content Quality
76
Structured Data
88
Bot Accessibility
84

Agent protocol panel

  • A2A agent cardNot found
  • OAuth discoveryPresent
  • MCP discoveryPresent
  • llms.txt validityPresent

Check results

Bot Accessibility

  • ✓No error status codespass
  • ~Response timepartial
  • ✓XML sitemap existspass
  • ✓AI agent accesspass
  • ✓Edge treatment of agent user-agentstracked, not scoredpass
  • ✓robots.txt existspass
  • ✗Content negotiation (Markdown)fail
  • ✓Declared AI usage preferencestracked, not scoredpass

Structured Data

  • ✓OpenGraph meta tagspass
  • ✓Semantic HTML elementspass
  • ✓Appropriate Schema.org typepass
  • ✓JSON-LD validpass
  • ~Heading hierarchypartial
  • ✓Schema.org JSON-LD presentpass
  • ~Schema.org completenesspartial

Content Quality

  • ✓FAQ contentpass
  • ✓Answer-first contentpass
  • ✓Content lengthpass
  • ✓Token efficiency (HTML-to-text ratio)pass
  • ✗Freshness signalsfail
  • ✗Author attributionfail
  • ✓Citation readinesspass
  • ✓Lists and tables for structured infopass

Agent Discovery

  • ✓llms.txt follows specpass
  • ✓llms.txt existspass
  • ✗MCP server cardtracked, not scoredfail
  • ✗Markdown alternate linksfail
  • ✗/.well-known/agent-card.jsonfail
  • ✓llms.txt links resolvepass

Agent Protocols

  • ✓Discoverable API endpointspass
  • ✓MCP endpointpass
  • ✗Action schemasfail
  • —/.well-known/ucpskip
  • ~Structured formspartial
  • —WebMCP imperative APItracked, not scoredskip
  • —WebMCP declarative APItracked, not scoredskip
  • ✓Reachable as Google-Agentpass
  • ✓Reachable as ChatGPT-Userpass
  • ✓Reachable as Perplexity-Userpass

Agent Auth

  • —MCP authorization (401 challenge → protected resource metadata)skip
  • ✓PKCE S256 supportpass
  • ✗Public API surfacefail
  • —Client ID Metadata Documents (bonus)skip
  • ✓OpenAPI specificationpass
  • ~Agent/bot auth documentationpartial
  • ✓OAuth discovery chain (RFC 9728 → RFC 8414)pass
  • ✓Developer portalpass
  • ✗Scoped API permissionsfail
  • ✓API catalog (RFC 9727)pass
  • —Agent operator signing directorytracked, not scoredskip

Technical

  • ✓HTTPSpass
  • ✓UTF-8 charsetpass
  • ✓Canonical URLspass
  • ✓Mobile viewportpass
  • ✓Content accessible without JSpass
  • ✓Security headerspass

Other

  • ✓nextjs-metadata-apipass
  • ~nextjs-static-generationpartial
  • ✗nextjs-well-known-servedfail
  • —local-business-hours-jsonldskip
  • —local-business-nap-structuredskip
  • —local-business-booking-accessibleskip

Score history

  • 74/100 · rubric v3.0
  • 80/100 · rubric v3.0
  • 79/100 · rubric v3.0
  • 48/100 · rubric v2.0
  • 48/100 · rubric v2.0
  • 46/100 · rubric v2.0
  • 45/100 · rubric v2.0
  • 31/100 · rubric v2.0

Related websites

Is your own site agent ready?

Check your own site →

Re-audit crewai.com