Cloudflare: the 360 agent-readiness check
Cloudflare scores 82 of 100 on Ora's agent-readiness scan, a B, read 9 November 2026. Of the five surfaces an agent acts on, Ora found 4: an MCP server, an OpenAPI specification, OAuth, a command line. Every act-layer surface in place, on a home page that is 0.2 percent text.
On 9 November 2026 the public site at cloudflare.com scored 82 of 100 on Ora's agent-readiness scan, a B, in Ora's Infrastructure category. Ora probes a site the way an agent would: it requests pages with the agents' own user agents, reads robots.txt, looks for the files agents read, and tries the API, MCP and payment surfaces. This check reads the act layer first, because that is what the directory records, then the door, what an agent can read, and whether the company is found and recommended. Ora's one-line summary: Cloudflare offers strong discovery and developer SDK coverage, but lacks declared OAuth scopes and scoped-permission documentation for agents.
The score
| Layer | Asks | Points | Share |
|---|---|---|---|
| Usability | Can agents use it | 90 of 121 | 74% |
| Access | Can agents read it | 57 of 63 | 90% |
| Discovery | Can agents find and recommend it | 15 of 18 | 83% |
| Payments | Can agents pay | 0 of 0 | none apply |
| Total | Grade B | 82 of 100 | 82% |
What an agent can do
The surfaces an agent acts on: an API it can find and call, an MCP server, an agent card, OAuth metadata, a command line. This is the layer the directory records, so it comes first.
In the directory, Cloudflare has an open MCP server with tools listed at https://docs.mcp.cloudflare.com/mcp, 2 tools listed, no authentication; the connector run of 4 November 2026 is on the entry page. Ora's MCP server check for the same domain reads pass; the two look for different things, the directory for a server that answers a handshake and lists tools, Ora for a server it can find from the site.
| Check | Result | Points | What Ora saw |
|---|---|---|---|
| MCP server / manifest mcp-server | Pass | 6 of 6 | MCP server connected via Streamable HTTP - docs-ai-search v0.5.0 (protocol 2025-11-25) |
| MCP well-known discovery mcp-well-known-discovery | Pass | 2 of 2 | MCP server discoverable via server-card.json at /.well-known/mcp/ |
| Public API with reachable endpoints public-api | Partial | 3 of 7 | API described in documentation at https://developers.cloudflare.com but no machine-verifiable API surface confirmed. Best-of-protocols score: 3/7. |
| Public API/docs linked from homepage public-api-docs | Pass | 3 of 3 | Documentation site found at https://developers.cloudflare.com |
| Developer portal developer-portal | Pass | 6 of 6 | Developer portal found at /developers |
| OpenAPI spec published openapi-spec | Pass | 7 of 7 | OpenAPI spec found at https://www.cloudflare.com/openapi.json (version: 3.1.0) |
| API catalog (RFC 9727) api-catalog-rfc9727 | Fail | 0 of 2 | No /.well-known/api-catalog found (RFC 9727) |
| A2A / agent-card a2a-agent-card | Fail | 0 of 2 | No A2A agent card found at /.well-known/agent-card.json |
| Agent discovery file agent-discovery-file | Pass | 2 of 2 | Agent Skills index (agentskills.io) found at /.well-known/agent-skills/index.json with 19 skill(s) |
| OAuth 2.0 support oauth-support | Pass | 5 of 5 | OAuth authorization server metadata at https://mcp.cloudflare.com |
| OAuth Protected Resource metadata (RFC 9728) oauth-protected-resource | Pass | 2 of 2 | no detail published |
| auth.md exists auth-md-exists | Pass | 2 of 2 | no detail published |
| WebMCP support webmcp | Pass | 5 of 5 | Imperative WebMCP API detected (document.modelContext.registerTool in inline script). |
| NLWeb /ask endpoint nlweb-ask | Fail | 0 of 1 | No NLWeb-conformant /ask endpoint found via GET or POST |
| CLI tool available cli-tool | Pass | 3 of 3 | CLI package found on npm: wrangler |
| Multi-language SDK packages rest-sdk-packages | Pass | 3 of 3 | SDK packages found across 3 ecosystems: npm, pypi, go |
| Rate limit response headers rate-limit-headers | Fail | 0 of 2 | No REST rate-limit headers found on probed endpoints |
| Idempotency-Key support idempotency-key-support | Fail | 0 of 3 | No REST Idempotency-Key support detected |
| JSON error responses json-error-responses | Pass | 4 of 4 | no detail published |
At the door
What the site answers when a request arrives with an agent's user agent, and what robots.txt says to agents.
| Check | Result | Points | What Ora saw |
|---|---|---|---|
| Not blocked by bot detection bot-detection | Pass | 2 of 2 | Site accessible to 4 agent user-agents (ChatGPT-User, OAI-SearchBot, Claude-User, PerplexityBot). |
| Agent crawler reachability agent-crawler-reachability | Pass | 2 of 2 | Reachable to every agent we tested - ChatGPT-User: reachable, OAI-SearchBot: reachable, Claude-User: reachable, PerplexityBot: reachable |
| robots.txt AI crawler policy robots-ai-policy-quality | Pass | 2 of 2 | AI search crawlers: allowed in 3 of 3 checks (3 crawlers on 1 page). AI training crawlers: allowed in 2 of 2 checks (2 crawlers on 1 page), not scored. |
| robots.txt agent-user policy robots-agent-user-policy | Pass | 2 of 2 | No applicable crawl or usage restriction found for 3 user-triggered agents (chatgpt-user, claude-user, perplexity-user) on 1 public page: https://cloudflare.com/. Declared policy only; |
| Content behind auth docs-auth-gate | Pass | 2 of 2 | All 5 sampled pages are publicly readable (3 with substantive content) |
| Homepage not hidden from search noindex-directives | Pass | 1 of 1 | No noindex on the homepage: no robots, googlebot or bingbot meta tag and no X-Robots-Tag header hides it from search. |
| Redirect hygiene redirect-hygiene | Pass | 1 of 1 | no detail published |
| Web Bot Auth directory web-bot-auth-directory | Fail | 0 of 2 | No /.well-known/http-message-signatures-directory found |
What an agent can read
Whether the text is in the first response, what the site publishes for agents, and how it describes itself to them.
| Check | Result | Points | What Ora saw |
|---|---|---|---|
| Content without JavaScript content-no-js | Partial | 2 of 3 | Homepage: 1612 chars with H1, but heading hierarchy skips H2 to H6; 0.2% content ratio is below the 5% target. 3 of 3 sampled inner pages have text without JavaScript (2 skipped). |
| Page token budget page-token-budget | Pass | 1 of 1 | All 6 measured pages fit an agent context budget (largest ~4K tokens) |
| Sitemap exists sitemap | Pass | 2 of 2 | Valid sitemap found at https://www.cloudflare.com/sitemap.xml with 1017 entries |
| Sitemap freshness (lastmod) sitemap-lastmod | Pass | 1 of 1 | no detail published |
| llms.txt exists llms-txt-exists | Pass | 1 of 1 | Found the llms.txt at https://developers.cloudflare.com/llms.txt. |
| llms.txt formatting llms-txt-formatting | Pass | 2 of 2 | The llms.txt is well-formatted: 140 lines with markdown links, 17,169 characters in total. |
| llms.txt links resolve llms-txt-links-resolve | Pass | 2 of 2 | no detail published |
| Markdown agent docs markdown-negotiation | Pass | 1 of 1 | Path-suffix markdown docs served with text/markdown content-type: /auth.md, /index.md |
| Markdown URL fallback markdown-url-fallback | Pass | 2 of 2 | no detail published |
| Bot-UA markdown serving agent-ua-markdown | Fail | 0 of 1 | No probed bot User-Agent (ChatGPT-User, Claude-User, Perplexity-User) receives markdown when requesting HTML. Optional: detect AI-bot UAs server-side and serve them a markdown representation directly. |
| Agent mode view agent-mode-view | Fail | 0 of 2 | ?mode=agent returns same content as homepage (no dedicated agent view) |
| JSON-LD structured data json-ld | Partial | 2 of 4 | JSON-LD Organization found - missing description on this entity |
| Organization schema completeness org-schema-completeness | Partial | 1 of 2 | Organization schema found but missing: contactPoint, address |
| JSON-LD entity linking (sameAs) json-ld-entity-linking | Pass | 2 of 2 | no detail published |
| Schema type breadth schema-type-breadth | Fail | 0 of 2 | No extended schema types found - AI can only answer basic questions about this entity |
| Metadata completeness metadata-completeness | Pass | 2 of 2 | All metadata signals present: canonical URL, lang="en", og:image, og:type |
| Agent instruction / when-to-use agent-instruction | Pass | 3 of 3 | no detail published |
Found and recommended
Whether an assistant can find the company by name, confirm what it is, and see it in the registries agents read.
| Check | Result | Points | What Ora saw |
|---|---|---|---|
| Brand name discoverability brand-search-accuracy | Partial | 1 of 3 | cloudflare.com ranks #6 for "Cloudflare" (searched your brand name alone: no main product term from your homepage qualified) |
| Wikipedia / Wikidata entity presence wikipedia-presence | Pass | 4 of 4 | Wikipedia "Cloudflare" and Wikidata Q4778915 both verified - domain confirmed on both sources |
| Developer resource discoverability agentic-search-specific | Pass | 3 of 3 | no detail published |
| Listed in MCP registries mcp-registry-listed | Pass | 1 of 1 | no detail published |
| NPM/PyPI SDK package npm-sdk-package | Pass | 1 of 1 | no detail published |
| ChatGPT app listed chatgpt-app-listed | Pass | 2 of 2 | no detail published |
| Registry branding registry-branding | Partial | 1 of 2 | MCP manifest has name and description but no icon at /.well-known/mcp/server-card.json |
| Listed on skills.sh skills-sh-listed | Pass | 1 of 1 | no detail published |
| ARD discovery ard-catalog | Fail | 0 of 1 | No /.well-known/ard.json, no same-site rel="ard" link, and no legacy /.well-known/ai-catalog.json |
Payments
The agent payment protocols Ora probes for. A site that sells nothing has nothing here, and Ora scores the layer out of zero when none applies. None of the 6 payment checks applied to cloudflare.com.
The fixes worth most points
Ora attaches an estimate to each failing or partial check: how many points the site would gain by passing it. These are the 5 with the largest estimates for Cloudflare, with what Ora observed. The wording of each fix is Ora's; the 28 checks it runs on an MCP server are listed with their layer and tier.
- Brand name discoverability: partial, 1 of 3, about 2.5 points to gain. Ora saw: cloudflare.com ranks #6 for "Cloudflare" (searched your brand name alone: no main product term from your homepage qualified)
- Scoped permissions: fail, 0 of 5, about 1.8 points to gain. Ora saw: No declared OAuth scopes, security schemes, or scoped-permission documentation found
- Public API with reachable endpoints: partial, 3 of 7, about 1.5 points to gain. Ora saw: API described in documentation at https://developers.cloudflare.com but no machine-verifiable API surface confirmed. Best-of-protocols score: 3/7.
- ARD discovery: fail, 0 of 1, about 1.2 points to gain. Ora saw: No /.well-known/ard.json, no same-site rel="ard" link, and no legacy /.well-known/ai-catalog.json
- REST typed error model: fail, 0 of 3, about 1.1 points to gain. Ora saw: No typed error model found in OpenAPI spec
Our read
Cloudflare passes every surface Ora tests on the act layer: a live MCP handshake with docs-ai-search version 0.5.0, a server card at /.well-known/mcp/, an OpenAPI 3.1.0 specification at cloudflare.com/openapi.json, OAuth authorization server metadata at mcp.cloudflare.com, wrangler on npm, SDKs in npm, PyPI and Go, an agent skills index with 19 skills, an llms.txt on the developer host and markdown twins served with text/markdown. It even registers a WebMCP tool in an inline script, which almost no company in this set does. The 82 rather than a higher mark comes from the edges: no declared OAuth scopes, no typed error model in the specification, no ARD catalog, a home page that is 0.2 percent text with a heading tree that skips from H2 to H6, and a brand search that places the domain sixth for its own name. The act layer is finished; the home page is where the points are left.
Test your own surfaces
The scan above is free and needs no account: enter a domain at ora.ai and read the same four layers for your own site. For an MCP server, Ora scans the server URL itself and runs 28 of its 132 public checks on it, which is why it is the check this directory recommends; the reasons, the limits and the alternatives are on their own page. The command below runs the same audit from a terminal and exits with 1 under the score you set, so it can gate a deploy.
npx ax@0.10 audit https://example.com --min-score 70All 360 checks, one company a day. Corrections to the corrections page.