cloudflare.com agentic web readiness

A Score 49 (coverage 30 + breadth 9 + conformance 10). 5 standards observed across 3 of 9 steps; 5 manifests present, 4 errors, 8 warnings. Checked 2026-10-18 22:06:00 UTC via www.cloudflare.com. This grades the agent-facing files published at cloudflare.com, not the organisation's products.

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

Coverage by step

01 Discovernothing observed 02 Identifynothing observed 03 PermitContent Signals Policy, auth.md, AI Crawler User-Agent Tokens in robots.txt 04 Readllms.txt 05 Actnothing observed 06 Coordinate 07 Paynothing observed 08 Presentnothing observed 09 Accountnothing observed

Manifests

Manifest	Result	Findings
Agentic Resource Discovery `/.well-known/ard.json`	absent HTTP 404
AI Catalog well-known file `/.well-known/ai-catalog.json`	absent HTTP 404
MCP Server Cards (SEP-2127) `/.well-known/mcp.json`	absent HTTP 200	a client-config map (mcpServers), not a SEP-2127 server card; /.well-known/mcp.json is superseded by <mcp-url>/server-card
Agent2Agent Protocol `/.well-known/agent.json`	errors HTTP 200	version missing skills[0].tags missing (required) skills[1].tags missing (required) supportedInterfaces missing; A2A 1.0 cards declare interfaces there (url, protocolBinding, protocolVersion) and the top-level url is the 0.3 shape defaultInputModes missing defaultOutputModes missing protocolVersion missing; clients cannot tell which A2A revision the card follows provider missing (organization, url) served at /.well-known/agent.json; A2A 0.3+ reads /.well-known/agent-card.json
llms.txt `/llms.txt`	valid HTTP 200
AGENTS.md `/AGENTS.md`	absent HTTP 404
api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs `/.well-known/api-catalog`	absent HTTP 404
AI Crawler User-Agent Tokens in robots.txt `/robots.txt`	valid HTTP 200	no Agentmap: line (optional convention pointing agents at /.well-known/ard.json)
security.txt (RFC 9116) `/.well-known/security.txt`	errors HTTP 200	Expires: missing (RFC 9116 requires it)
auth.md `/auth.md`	valid HTTP 200

What an agent can call

A2A agent Cloudflare Site Agent at https://www.cloudflare.com/.well-known/agent.json, skills: Site Context, Page Markdown
llms.txt: Cloudflare, 90 links
robots.txt AI policy: allows GPTBot, ChatGPT-User, anthropic-ai, Google-Extended, PerplexityBot, CCBot, cohere-ai; unlisted crawlers allowed

Standards observed

llms.txt https://cloudflare.com/llms.txt
Content Signals Policy https://cloudflare.com/robots.txt
auth.md https://cloudflare.com/auth.md
AI Crawler User-Agent Tokens in robots.txt https://cloudflare.com/robots.txt
Agent2Agent Protocol

Cheapest next steps

Agentic Resource Discovery: a catalog at /.well-known/ard.json lets agents discover your APIs, MCP servers and data in one fetch
AGENTS.md: instructions for coding agents working on or with the site
api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs: an RFC 9727 linkset pointing at your OpenAPI description

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