agent-ready.dev agentic web readiness

A+ Score 95 (coverage 70 + breadth 15 + conformance 10). 13 standards observed across 7 of 9 steps; 9 manifests present, 1 error, 9 warnings. Checked 2026-10-18 23:43:00 UTC. This grades the agent-facing files published at agent-ready.dev, not the organisation's products.

Badge for a README: ![agentic web grade](https://agenticweb.wiki/badge/agent-ready.dev.svg) · JSON · Markdown · Re-check now

Coverage by step

Manifests

What an agent can call

• A2A agent agent-ready at https://agent-ready.dev/api/v1/a2a, skills: Scan a site, Get a scan by id, Ask Agent Ready
• API description https://agent-ready.dev/api/v1/openapi.json (application/openapi+json;version=3.1)
• API description https://agent-ready.dev/api/v1/openapi.json (application/openapi+json;version=3.1)
• API description https://agent-ready.dev/docs/api (text/html)
• API description https://agent-ready.dev/.well-known/mcp.json (application/json)
• API description https://agent-ready.dev/mcp (text/html)
• API description https://agent-ready.dev/.well-known/mcp.json (application/json)
• API description https://agent-ready.dev/mcp (text/html)
• API description https://agent-ready.dev/api/v1/openapi.json (application/openapi+json;version=3.1)
• API description https://agent-ready.dev/what-is-nlweb (text/html)
• llms.txt: Agent Ready, 116 links
• robots.txt AI policy: blocks CCBot, Bytespider; allows GPTBot, OAI-SearchBot, ClaudeBot, Google-Extended, PerplexityBot, Applebot-Extended, meta-externalagent, Amazonbot, cohere-ai, Diffbot, YouBot; unlisted crawlers partial
• OAuth protected resource https://agent-ready.dev/api/v1/mcp, authorization servers: https://agent-ready.dev

Standards observed

• Agent2Agent Protocol https://agent-ready.dev/.well-known/agent-card.json
• Universal Commerce Protocol https://agent-ready.dev/.well-known/ucp
• llms.txt https://agent-ready.dev/llms.txt
• AGENTS.md https://agent-ready.dev/AGENTS.md
• Content Signals Policy https://agent-ready.dev/robots.txt
• Web Bot Auth HTTP Message Signatures https://agent-ready.dev/.well-known/http-message-signatures-directory
• AI Catalog well-known file https://agent-ready.dev/.well-known/ai-catalog.json
• api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs https://agent-ready.dev/.well-known/api-catalog
• agent-permissions.json https://agent-ready.dev/.well-known/agent-permissions.json
• auth.md https://agent-ready.dev/auth.md
• AI Crawler User-Agent Tokens in robots.txt https://agent-ready.dev/robots.txt
• agents.json https://agent-ready.dev/.well-known/agents.json
• OAuth Protected Resource and Authorization Server Metadata (as used for agent authorization) https://agent-ready.dev/.well-known/oauth-protected-resource

Cheapest next steps

1. Agentic Resource Discovery: a catalog at /.well-known/ard.json lets agents discover your APIs, MCP servers and data in one fetch

How the grade is made

+10 per lifecycle step with a standard observed, counting manifests that validate or that the probe rule for the standard recognises (a valid MCP server card counts for MCP; max 90); +3 per observed standard beyond the first two (max 15); conformance +15 (+10 with one manifest) minus 5 per agent-facing manifest with errors, never below 0 (security.txt is reported, not scored). A+ >= 60, A >= 45, B >= 30, C >= 20, D >= 10. Errors are specification violations; warnings are best-practice gaps. Only public paths are fetched, without credentials, so standards that need a login (skipped in the probe) are not counted either way. The same report is the validate_manifest tool on the MCP server.

JSON · Markdown · probe rules