Autonomous agents
Claude-Web is a bot operated by Anthropic that browses the web on its own to finish multi-step tasks. Claude-Web is an AI-related agent operated by Anthropic. Whether it honours robots.txt is undocumented, and a request claiming to be Claude-Web can be checked against a published IP range file.
Request says
"Claude-Web"
Checked against
Anthropic's published IP ranges
Live check
Paste the address from the log line. It is checked against what the operator publishes.
Reference
| User agent | Claude-WebToken only: match on the substring. |
|---|---|
| Operator | Anthropic |
| Purpose | Autonomous agents |
| Respects robots.txt | No policy |
| Verification method | IP rangesPublished IP range file A legacy token that predates the current ClaudeBot naming. Site owners still see it in old logs and old robots.txt files; check the published prefix file before trusting it. |
| Crawl pattern | Not published |
| Robots.txt tokens | Claude-Web |
| Operator documentation | https://support.claude.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler |
Claude-Web is an AI-related agent operated by Anthropic. It's currently unclear exactly what it's used for, since there's no official documentation. If you can provide more detail, please contact us.
robots.txt
Paste one at the root of your domain. Rules are per token.
User-agent: Claude-Web
Disallow: /User-agent: Claude-Web
Allow: /User-agent: Claude-Web
Allow: /
Disallow: /account/
Disallow: /checkout/
Disallow: /searchEdit the Disallow paths to match your own URLs.
Blocking Claude-Web stops automated sessions that fill forms, click through flows and read pages the way a logged-in user would. Rate limits and challenges usually work better here than a robots.txt line.
Build a file for every crawlerFAQ
Claude-Web is a bot operated by Anthropic that browses the web on its own to finish multi-step tasks. Claude-Web is an AI-related agent operated by Anthropic. Whether it honours robots.txt is undocumented, and a request claiming to be Claude-Web can be checked against a published IP range file.
Not documented. No operator statement says whether Claude-Web reads robots.txt, so add the rule but verify in your logs that the requests actually stop.
A legacy token that predates the current ClaudeBot naming. Site owners still see it in old logs and old robots.txt files; check the published prefix file before trusting it. The reference is published at https://claude.com/crawling/bots.json.
Add the Claude-Web 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 Claude-Web stops automated sessions that fill forms, click through flows and read pages the way a logged-in user would. Rate limits and challenges usually work better here than a robots.txt line.