AI search crawlers
Cloudflare-AutoRAG is a bot operated by Cloudflare that indexes pages so an AI answer engine can cite them. AutoRAG is an all-in-one AI search solution. It is documented as honouring robots.txt, but no IP range list or reverse-DNS convention is published, so a request carrying this user agent cannot be proven genuine.
Request says
"Cloudflare-AutoRAG"
Checked against
Nothing published
Live check
No operator check exists for Cloudflare-AutoRAG. This still shows what the address really is.
Reference
| User agent | Cloudflare-AutoRAGToken only: match on the substring. |
|---|---|
| Operator | Cloudflare |
| Purpose | Collects data for AI search |
| Respects robots.txt | Honours |
| Verification method | Claim onlyNone published, user agent only No IP range file and no reverse-DNS convention have been published for this agent. The user-agent string is the only signal, and any client can send it, so treat a match as a claim rather than proof. |
| Crawl pattern | Not published |
| Robots.txt tokens | Cloudflare-AutoRAG |
| Operator documentation | None published |
AutoRAG is an all-in-one AI search solution.
robots.txt
Paste one at the root of your domain. Rules are per token.
User-agent: Cloudflare-AutoRAG
Disallow: /User-agent: Cloudflare-AutoRAG
Allow: /User-agent: Cloudflare-AutoRAG
Allow: /
Disallow: /account/
Disallow: /checkout/
Disallow: /searchEdit the Disallow paths to match your own URLs.
Blocking Cloudflare-AutoRAG takes the site out of the index behind its answers, so it stops being cited there. If referral traffic from AI answers matters to you, block the training crawler instead and leave this one alone.
Build a file for every crawlerFAQ
Cloudflare-AutoRAG is a bot operated by Cloudflare that indexes pages so an AI answer engine can cite them. AutoRAG is an all-in-one AI search solution. It is documented as honouring robots.txt, but no IP range list or reverse-DNS convention is published, so a request carrying this user agent cannot be proven genuine.
Yes. The operator documents that Cloudflare-AutoRAG reads robots.txt and follows Disallow rules for its own token. Rules take effect on the next fetch of the file, which can be hours or days after you publish them.
You cannot, at least not from the request itself. No IP range file and no reverse-DNS convention have been published for this agent. The user-agent string is the only signal, and any client can send it, so treat a match as a claim rather than proof. Compare the source IP against hosting and datacenter ranges instead, and rate limit anything that behaves like a crawler.
Add the Cloudflare-AutoRAG token to robots.txt with Disallow: /. If the crawler ignores robots.txt, match the user agent at your CDN or reverse proxy and return 403 there instead.
Blocking Cloudflare-AutoRAG takes the site out of the index behind its answers, so it stops being cited there. If referral traffic from AI answers matters to you, block the training crawler instead and leave this one alone.