# Cloudflare-AutoRAG

> The crawler behind Cloudflare's AI Search / AutoRAG, which indexes a website into a retrieval index for an application. Cloudflare's own documentation warns that a bot-blocking rule on your zone will also stop this crawler and tells you to allow-list it.

| field | value |
|---|---|
| operator | Cloudflare |
| category | AI search crawlers |
| robots.txt token | `Cloudflare-AutoRAG` |
| user-agent contains | `Cloudflare-AutoRAG` |
| robots.txt | obeys robots.txt (documented) |
| verify by | no published verification method |
| published IP ranges | none published |
| prefixes mirrored | 0 IPv4 / 0 IPv6 |
| operator docs | https://developers.cloudflare.com/ai-search/ |
| last reviewed | 2026-09-14 |

## What blocking it costs you

Applications built on Cloudflare AI Search cannot retrieve your pages. If you are the one building the index over your own site, blocking it breaks your own product.

## Full user-agent string

```
Cloudflare-AutoRAG
```

## Block it

```
User-agent: Cloudflare-AutoRAG
Disallow: /
```

## Allow it

```
User-agent: Cloudflare-AutoRAG
Allow: /
```

## Ask this page a question, with one GET

A question about this page, answered by a call you can make right now — no key, no account, no JSON-RPC, nothing to assemble. The query string is already filled in with this page's own subject.

- **How do I prove a request really is Cloudflare-AutoRAG?**  
  `curl -s 'https://www.pathwren.workers.dev/tools/verification-methods?crawler=cloudflare-autorag&s=client-dossiers'`  
  The verification method its operator actually publishes — published IP ranges, reverse DNS, or nothing at all — and the mirror of it on this host.

Every parameter above is a value the endpoint reads, not an address it visits: nothing is fetched on your behalf. Called without any parameter, each endpoint returns its own specification instead of an error.

JSON: https://www.pathwren.workers.dev/crawler/cloudflare-autorag.json · index: https://www.pathwren.workers.dev/llms.txt