Claude-User
Anthropic's agent for fetching a site when a Claude user asks a question that needs it. Anthropic presents robots.txt as the way to control these user-initiated requests.
| Operator | Anthropic |
|---|---|
| Purpose | Browsing — Claude (user requests) |
| robots.txt token | Claude-User |
| User-Agent | Full string not published by the operator |
| Obeys robots.txt | Yes, according to the publisher |
| Official IP ranges | https://claude.com/crawling/bots.json — 14 ranges, list dated 2026-10-20 |
| Reverse DNS | Not documented |
| Official documentation | https://support.claude.com/en/articles/8896518 |
Live activity of Claude-User
No visit from Claude-User recorded on iabig.com over the last 30 days.
Last updated: 2026-10-25 12:07:01 UTC. See the Observatory
What Claude-User does
Claude-User serves Claude users: when someone asks a question, Claude may access websites with this agent to answer it. It does not crawl the web systematically.
What Anthropic states:
- Claude-User lets site owners control which sites can be accessed through these user-initiated requests.
- Disabling it prevents Anthropic's system from retrieving your content in response to a user query, which may reduce your visibility in user-directed web search.
- Anthropic's bots honor robots.txt, and no exception is stated for this agent.
This sets Anthropic apart from several other vendors. OpenAI, Perplexity and Meta all say their user-triggered agents may not follow robots.txt, whereas Anthropic presents Claude-User as controllable through that file.
As with Anthropic's other bots, authentication relies on the shared IP list, which cannot tell Claude-User apart from ClaudeBot or Claude-SearchBot. No full user-agent string is published; only the Claude-User name is documented.
Blocking Claude-User has no bearing on training, which is ClaudeBot's job, or on search indexing ahead of time, which is handled by Claude-SearchBot.
Block or allow Claude-User
Claude can no longer read your pages when a user asks it to, which may reduce your visibility in answers based on live retrieval.
To block it, add this to your robots.txt:
User-agent: Claude-User
Disallow: /To allow it explicitly (copy any private rules you have):
User-agent: Claude-User
Allow: /A group naming Claude-User replaces the User-agent: * group for it. Build a complete robots.txt with the generator and check it with the tester.
Verify a Claude-User visit
Anyone can write “Claude-User” in a User-Agent. Paste the IP address and User-Agent from your logs into the IP verifier to know whether the visit is genuine.
Other Anthropic crawlers
- ClaudeBot — Training
- Claude-SearchBot — Search