Agent Readiness Compare

Cloudflare isitagentready.com and URL Scanner

Scanner operated by Cloudflare.

In short

Free Cloudflare scanner launched in April 2026 that checks a site against named web and agent standards, assigns a level from 0 to 5, and is also built into URL Scanner and exposed over MCP. It ranks 5 of 10 on the ten-criterion rubric with 56 of 100, earning most on journey 15 of 15 and standards 5 of 5.

What it is

Free Cloudflare scanner launched in April 2026 that checks a site against named web and agent standards, assigns a level from 0 to 5, and is also built into URL Scanner and exposed over MCP.

Operator: Cloudflare. Type: Scanner. Home page: isitagentready.com.

Ten-criterion rubric

Cloudflare scanner: every scored part of the ten-criterion rubric, read 5 November 2026
CriterionPointsWhat the source says
Journey: find4 of 4discoverability and bot-access checks 1
Journey: read4 of 4content accessibility, markdown negotiation 1
Journey: use4 of 4MCP Server Card, A2A Agent Card, Agent Skills, API Catalog 1
Journey: pay3 of 3x402, MPP, UCP, ACP and AP2, scored for sites with e-commerce signals 1
Checks5 of 1523 checks in 5 categories 1
Real agents0 of 15fetches files, headers and DNS records; runs no agent 1
Open method: catalog3 of 3every check documented 1
Open method: weights0 of 3levels are defined by check combinations and the launch post says commerce checks do not count; no per-check or per-category weights published 1
Open method: scale2 of 2levels 0 (Not Ready) to 5 (Agent-Native) 1
Open method: changes2 of 2launch post dated 2026-04-17; a changelog entry dated 2026-05-12 adds six readiness scores to URL Scanner reports 2
Standards: cites3 of 3a Spec link on each of its 23 checks in llms-full.txt (100 percent) 1
Standards: maintains2 of 2Cloudflare proposed the agent-skills discovery index and co-launched the x402 Foundation with Coinbase 3
Dev fit: api3 of 3POST /api/scan 1
Dev fit: mcp3 of 3Streamable HTTP MCP server at /mcp 4
Dev fit: cli0 of 2the scanner documents a POST API and an MCP server; no command-line client 1
Dev fit: ci0 of 2no CI gate documented on the scanner or in the launch post 1
Peers: ranking2 of 6Cloudflare Radar publishes an 'Adoption of AI agent standards' dataset from scans of the 200,000 most visited domains, updated weekly (post dated 2026-04-17); no site-by-site leaderboard 3
Peers: size4 of 4200,000 most visited domains scanned for the Radar dataset 3
Fixes: guidance4 of 4fix instructions for every failing check 1
Fixes: brief3 of 3format agent returns one markdown document of fixes 1
Fixes: applies0 of 3the agent format returns one markdown document of fix instructions; it changes nothing 1
Repeat scans0 of 5no repeat-scan claim or data 1
Free: free3 of 3free, no sign-up 5
Free: limits2 of 2no stated cap 5

Total 56 of 100, rank 5 of 10. The ranking is on the pick page; the same cells are on the evidence page.

Seven-criterion reading

Cloudflare scanner: the seven rubric criteria, scored 1 to 5 on evidence read on 2026-11-04
CriterionScoreEvidence
Coverage3Its 23 checks map to about 11 of 24 AgentReady identifiers by our count; it does not test JavaScript-only content, status codes, JSON-LD or code fences. 4
Transparency3Every check is named and linked to its standard, but no weights or level thresholds are published. 5
Reproducibilitysame on 3 of 3 repeatsTwo live scans (POST /api/scan, documented in its llms-full.txt) of netlify.com, prisma.io and tavily.com about three minutes apart returned the same percentage each time (67, 40, 40), which fits its deterministic file and header probes. 1
Access5Free web tool with no sign-up, a POST /api/scan endpoint, an MCP endpoint, URL Scanner integration and Radar adoption data. 4
Remediation4A copyable prompt per failing check for coding agents, plus a skill document per standard; advice is labelled AI-generated. 3
Independence of method3The dimensions are Cloudflare's own, but each check points at an external standard (RFC 9309, RFC 9727, RFC 9728, MCP, x402). 3
FreshnessundatedThe check list grew from the April launch list to 23 standards including ARD, DNS-AID and Personal Agent Protocol by 2026-11-04; no dated changelog was found. 4

Total of the five numeric criteria: 18 of 25, rank 3 of 6 (tied). Reproducibility and freshness are shown and not summed. Scale 1 to 5, scored by this site on published evidence; reproducibility is a repeat-run result, not a score.

The seven criteria are defined on the method page; this is the reading of 4 November, kept beside the ten-criterion rubric above. Scores are this site's reading of the cited evidence, not the scanner's own claim.

What the sources say

  • Cloudflare introduced isitagentready.com in a blog post published 17 April 2026.3 dated 2026-04-17
  • At launch the score used four dimensions: Discoverability, Content, Bot Access Control and Capabilities; commerce checks (x402, UCP, ACP) were reported but did not count toward the score.3 dated 2026-04-17
  • On 2026-11-04 the site's llms.txt says it checks 23 standards across 5 categories, and its MCP manifest describes a readiness level from 0 to 5.4 dated 2026-11-04
  • Radar scanned the 200,000 most visited domains: 78 percent had a robots.txt, 4 percent declared Content Signals and 3.9 percent passed markdown negotiation.3 dated 2026-04-17
  • Agent Readiness scores were added to URL Scanner reports in the Cloudflare dashboard on 12 May 2026, with six categories including Basic Web Presence and Commerce.2 dated 2026-05-12
  • The URL Scanner API returns agent readiness results when the scan request sets options.agentReadiness to true; it needs a Cloudflare account ID and API token.3
  • The site exposes a stateless MCP server with a scan_site tool and an Agent Skills index with a skill document per standard.3
  • llms.txt is not checked by default; it can be added by customising the scan.3
  • Fix advice is generated by AI, and the page states that Cloudflare assumes no liability for actions taken on it.5

Pricing and access

Free on isitagentready.com with no sign-up; the URL Scanner API route needs a Cloudflare account and API token (read 2026-11-04). 3

What it does not do

  • Does not run an agent against the site or test a task end to end.
  • Does not check whether the answer is in the initial HTML or whether missing pages return real 404s.
  • Does not rank sites against each other on a public leaderboard.

In the Scanner Concordance

In the 2026-11-04 Concordance this scanner scored 52 of 60 domains, from 0 to 100 with a median of 20 and a mean of 34.0.

It returned no score for 8 domains: 7 (scanner could not fetch the site (HTTP 403)); 1 (scanner could not fetch the site (HTTP 404)).

Rank correlation of Cloudflare with each other scanner, on the domains both scored
ScannerShared domainsSpearman
Ora520.79
is-agentic.com400.72
Mintlify180.39

Sources

  1. isitagentready.com/llms-full.txt. https://isitagentready.com/llms-full.txt, read 2026-11-05.
  2. developers.cloudflare.com/changelog/post/2026-05-12-URL-scanner-report-agent-readiness. https://developers.cloudflare.com/changelog/post/2026-05-12-URL-scanner-report-agent-readiness/, read 2026-11-05.
  3. blog.cloudflare.com/agent-readiness. https://blog.cloudflare.com/agent-readiness/, read 2026-11-05.
  4. isitagentready.com/llms.txt. https://isitagentready.com/llms.txt, read 2026-11-05.
  5. isitagentready.com. https://isitagentready.com/, read 2026-11-05.
  6. Ora complete public documentation (llms-full.txt). https://ora.ai/llms-full.txt, read 2026-11-04.

Last reviewed 2026-11-05