Is anthropic.com agent ready?

anthropic.com is partly agent ready: it scores 52/100 (grade C) on the w2agent rubric. Weakest areas: Agent Protocols (25), Agent Auth (33), Agent Discovery (34), Structured Data (35).

52/ 100
Grade: C

Last checked · Platform: nextjs

Scored Oct 14, 2026 · Rubric v3.0

Changed since last check

+3 points since the previous check (2026-09-16)

Fixed: Agent/bot auth documentation

Regressed: llms.txt links resolve

Changed: Freshness signals (fail → partial)

Category scores

Technical
87
Agent Auth
33
Agent Discovery
34
Agent Protocols
25
Content Quality
79
Structured Data
35
Bot Accessibility
79

Agent protocol panel

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

Check results

Bot Accessibility

  • ✓No error status codespass
  • ✗Response timefail
  • ✓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 scoredskip

Structured Data

  • ✓OpenGraph meta tagspass
  • ✓Semantic HTML elementspass
  • ✗Appropriate Schema.org typefail
  • —JSON-LD validskip
  • ~Heading hierarchypartial
  • ✗Schema.org JSON-LD presentfail
  • ✗Schema.org completenessfail

Content Quality

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

Agent Discovery

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

Agent Protocols

  • ✗Discoverable API endpointsfail
  • ✗MCP endpointfail
  • ✗Action schemasfail
  • —/.well-known/ucpskip
  • ✗Structured formsfail
  • —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 supportfail
  • ~Public API surfacepartial
  • —Client ID Metadata Documents (bonus)skip
  • ✗OpenAPI specificationfail
  • ✓Agent/bot auth documentationpass
  • ✗OAuth discovery chain (RFC 9728 → RFC 8414)fail
  • ✓Developer portalpass
  • ✗Scoped API permissionsfail
  • ✗API catalog (RFC 9727)fail
  • —Agent operator signing directorytracked, not scoredskip

Technical

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

Other

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

Score history

  • 52/100 · rubric v3.0
  • 49/100 · rubric v3.0
  • 51/100 · rubric v3.0
  • 54/100 · rubric v2.0
  • 54/100 · rubric v2.0
  • 54/100 · rubric v2.0
  • 54/100 · rubric v2.0
  • 41/100 · rubric v2.0
  • 41/100 · rubric v2.0
  • 41/100 · rubric v2.0
  • 40/100 · rubric v2.0

Related websites