how we rate.

6 binary criteria per level. need 4/6 to pass.

your level is the highest one you pass. L0 means no level passed yet.

L1

Basic Accessibility

can agents read your content?

  • Uses semantic HTML elements (header, nav, main, article, section, footer) instead of just divs l1_semantic_html
  • Has proper meta tags (title, description, og:tags, twitter:card) l1_meta_tags
  • Includes Schema.org JSON-LD structured data l1_schema_org
  • Does not block automated access with CAPTCHAs on public content l1_no_captcha
  • Content is server-side rendered (visible in HTML source, not just JS-rendered) l1_ssr_content
  • Uses clean, readable URLs (no excessive query params or hash fragments) l1_clean_urls

L2

Discoverability

can agents find things on your site?

  • Has a robots.txt that allows legitimate bot access l2_robots_txt
  • Provides an XML sitemap l2_sitemap
  • Has a /llms.txt file describing the site for LLMs l2_llms_txt
  • Publishes an OpenAPI/Swagger specification for its API l2_openapi_spec
  • Has comprehensive, machine-readable documentation l2_documentation
  • Primary content is text-based (not locked in images/videos/PDFs) l2_text_content

L3

Structured Interaction

can agents talk to your APIs?

  • Provides a structured REST or GraphQL API l3_structured_api
  • API returns JSON responses with consistent schema l3_json_responses
  • API supports search and filtering parameters l3_search_filter_api
  • Has an A2A agent card at /.well-known/agent.json l3_a2a_agent_card
  • Rate limits are documented and return proper 429 responses with Retry-After l3_rate_limits_documented
  • API returns structured error responses with error codes and messages l3_structured_errors

L4

Agent Integration

can agents do real work on your site?

  • Provides an MCP (Model Context Protocol) server l4_mcp_server
  • Supports WebMCP for browser-based agent interaction l4_webmcp
  • API supports write operations (POST/PUT/PATCH/DELETE), not just reads l4_write_api
  • Supports agent-friendly authentication (API keys, OAuth client credentials) l4_agent_auth
  • Supports webhooks for event notifications l4_webhooks
  • Write operations support idempotency keys l4_idempotency

L5

Autonomous Operation

can agents operate autonomously?

  • Supports event streaming (SSE, WebSockets) for real-time updates l5_event_streaming
  • Supports agent-to-agent capability negotiation l5_agent_negotiation
  • Has a subscription/management API for agents l5_subscription_api
  • Supports multi-step workflow orchestration l5_workflow_orchestration
  • Can proactively notify agents of relevant changes l5_proactive_notifications
  • Supports cross-service handoff between agents l5_cross_service_handoff