Assistant fetchers
Claude-User is a bot operated by Anthropic that fetches single pages on demand for an AI assistant. Claude-User is dispatched by Anthropic's Claude AI assistant in response to user prompts, when it needs to fetch content to include in its answers. It honours robots.txt, and a request claiming to be Claude-User can be checked against a published IP range file.
Request says
"Claude-User/1.0"
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 | Mozilla/5.0 (compatible; Claude-User/1.0; +Claude-User@anthropic.com) |
|---|---|
| Operator | Anthropic |
| Purpose | Assistant fetchers |
| Respects robots.txt | Honourssource |
| Verification method | IP rangesPublished IP range file Fired when a Claude user asks about a specific page, so it arrives one URL at a time. Covered by the same published prefix file as ClaudeBot. |
| Crawl pattern | Not published |
| Robots.txt tokens | Claude-User |
| 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-User is dispatched by Anthropic's Claude AI assistant in response to user prompts, when it needs to fetch content to include in its answers.
robots.txt
Paste one at the root of your domain. Rules are per token.
User-agent: Claude-User
Disallow: /User-agent: Claude-User
Allow: /User-agent: Claude-User
Allow: /
Disallow: /account/
Disallow: /checkout/
Disallow: /searchEdit the Disallow paths to match your own URLs.
Blocking Claude-User means a person who asks about one of your URLs gets an error instead of a summary. That is a support and reputation trade-off, not a training one.
Build a file for every crawlerFAQ
Claude-User is a bot operated by Anthropic that fetches single pages on demand for an AI assistant. Claude-User is dispatched by Anthropic's Claude AI assistant in response to user prompts, when it needs to fetch content to include in its answers. It honours robots.txt, and a request claiming to be Claude-User can be checked against a published IP range file.
Yes. The operator documents that Claude-User 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.
Fired when a Claude user asks about a specific page, so it arrives one URL at a time. Covered by the same published prefix file as ClaudeBot. The reference is published at https://claude.com/crawling/bots.json.
Add the Claude-User 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-User means a person who asks about one of your URLs gets an error instead of a summary. That is a support and reputation trade-off, not a training one.