Live answer fetcher from Anthropic
Claude-User
In short
Claude-User is Anthropic's live answer fetcher. The token to write in robots.txt is Claude-User. Check a visitor against the operator's published IP list. Unlike OpenAI and Perplexity, Anthropic says its user-triggered fetcher honours robots.txt. On robots.txt, Anthropic: Claude-User allows site owners to control which sites can be accessed through user-initiated requests; disabling it stops retrieval for user queries.
- Operator
- Anthropic
- Purpose
- Live answer fetch All live answer fetch rows. Fetches a page because a person asked an assistant about it, one request at a time.
- User-agent string
- No exact string is published. What the operator or a third party says: Contains "Claude-User"; no full string published
- robots.txt token
Claude-User- Respects robots.txt
Yes, per operator
Anthropic: Claude-User allows site owners to control which sites can be accessed through user-initiated requests; disabling it stops retrieval for user queries. Source, read 2026-11-04.
- Verification
Published IP list (JSON)
Match the source address of a request against the operator's published list. Documentation, read 2026-11-04.
- IP ranges
- claude.com/crawling/bots.json
- Rate behaviour
- Respects Crawl-delay where appropriate, per Anthropic.
- Block rate
-
8.1% of 5,938 top-10,000 sites with a parsed robots.txt disallow
Claude-Userat the root (479 sites). 4.5% name it; 3.6% refuse it only through a * group. Rank 24 of 31 tokens measured.Across all 8,624 parsed robots.txt files in the crawl: 5.7% (3.1% named). Crawl of 2026-11-04; report.
- Documentation
- support.claude.com, read 2026-11-04.
Note. Unlike OpenAI and Perplexity, Anthropic says its user-triggered fetcher honours robots.txt.
Allow and refuse lines
To allow Claude-User
User-agent: Claude-User Allow: /
To refuse Claude-User
User-agent: Claude-User Disallow: /
Refusing or allowing in robots.txt states a preference. Enforcement of a refusal belongs in your WAF; see how to verify the identity above.
Anthropic in the Verification Ledger
One shared IP list for all three bots; no key directory at claude.ai or claude.com (404, 2026-11-04); nothing for Claude in Chrome. All operators.
- IP lists
- Reverse DNS
- publishes nothing
- Key directory
- publishes nothing
- Cloudflare
- not confirmed on Radar (directory slug not found, 2026-11-04)
- Visa TAP registry
- no public operator-level registration found (checked 2026-11-04)
- Mastercard Agent Pay
- no public operator-level registration found (checked 2026-11-04)
In the news
- 2026-10-20Anthropic refreshes its crawler IP list
Other Anthropic rows
- ClaudeBot Training
- Claude-SearchBot Search index
- anthropic-ai (legacy token) Training
- Claude in Chrome Task agent
- Claude Duet cloud browser Task agent
- Claude computer use (API tool) Task agent
Sources
Last reviewed 2026-11-04