◎ Discry Score
cloudflare.com
devtools · API
A
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 96 (A)
Discry your API →
DEVTOOLS · RANK #1 OF 39

Cloudflare is Agent-Ready to agents.

Discry independently scored how well an AI agent can discover and understand the Cloudflare API from what’s public — not whether it’s usable. Below: every signal we checked, what’s costing the score, and what to change.

Discry your API — freeView the docs ↗

SCORED UNDER RUBRIC 1.2 · A full re-launch under Discry Score 2.5 — a new behavioral instrument, not comparable to these scores — is in progress.

Discovery

45% of score · 95/100
OpenAPI specA machine-readable OpenAPI/Swagger spec agents can parse.Pass
llms.txtAn llms.txt index that points agents to the docs that matter.Pass
llms.txt qualityThe llms.txt is focused, current, and well under the size budget.Pass
llms-full.txtA full-text bundle agents can load in one request.Pass
AGENTS.mdAn AGENTS.md that tells coding agents how to build on the API.Pass
.well-known/mcp.jsonA discoverable MCP manifest at a well-known path.Fail
MCP registryThe API is listed in a public MCP registry.Pass
robots.txt AI directivesrobots.txt allows (or explicitly guides) AI crawlers.Pass
SitemapA sitemap so agents can enumerate the docs surface.Pass

Comprehension

55% of score · 96/100
Task-oriented descriptionsEndpoints described by what they accomplish, not just their shape.Pass
Realistic examplesRunnable, real-world request/response examples.Pass
Multi-step workflowsDocs that chain calls into complete jobs an agent can follow.Pass
Error-recovery guidanceDocumented failure modes and how to recover from them.Partial
Answer-first formatThe answer leads; preamble does not bury it.Pass
Capability boundariesClear limits — what the API can and cannot do.Pass
Naming consistencyConsistent, predictable naming across endpoints.Pass
Heading hierarchyClean heading structure agents can navigate.Pass
Markdown docsDocs available as clean markdown, not JS-rendered HTML only.Pass
Token efficiencyDocs are concise enough to fit an agent context window.Pass

What we found

  • Cloudflare has the best llms.txt architecture observed: a concise index (15KB) linking to per-product llms.txt files, each of which links to product-scoped llms-full.txt — perfect progressive disclosure for agents.
  • The robots.txt explicitly allows all AI uses (ai-train=yes, search=yes, ai-input=yes) with detailed Content-Signal explanations citing EU copyright directive.
  • AGENTS.md exists across 4+ repos (agents, workers-sdk, cloudflare-docs, mcp) — Cloudflare is clearly investing in agent-first developer tooling.
  • Multiple official MCP servers cover different product areas (Workers, DNS, R2, D1, Browser Rendering, AI Gateway, Docs) — the most comprehensive official MCP coverage observed.
  • The only discovery gap is .well-known/mcp.json, which would provide a single machine-discoverable entry point to all these MCP servers.

What to change

Prioritized by impact on discoverability. You (or your docs platform) deploy these — Discry never touches your API.

  1. 01Add .well-known/mcp.json that catalogs all official Cloudflare MCP servers with their capabilities — this would be the first multi-server mcp.json in the industry.
  2. 02Add explicit error recovery guidance to the API reference (most error codes currently lack actionable 'what to do next' steps).
  3. 03Consider publishing an idempotency key mechanism for write operations to help agents safely retry failed mutations.

Execution coverage · INFORMATIONAL, UNSCORED

Whether an agent can actually complete a call and recover from errors is the deeper Audit layer — documented here, but not part of the Discry Score.

API token (Bearer)API key + email (legacy)OAuth2✓ Error format documented✓ Rate limits documented✓ Pagination documented✕ Idempotency documented

Comprehensive execution documentation with OpenAPI-driven API reference, structured JSON error responses, rate limiting with headers, cursor-based pagination. Multiple official MCP servers demonstrate practical agent integration patterns.

See your own Discry Score.

Drop your API docs URL. See what an agent sees — in 60 seconds, free.

Discry your API — free