Claude-SearchBot: what it is, what it does with your content, and what blocking it costs
What Claude-SearchBot is
Claude-SearchBot builds the retrieval index that Anthropic answers from. This is the category that decides whether you can be cited right now: when someone asks a question and the assistant goes looking for sources, it searches an index this crawler built. Blocking it removes you from those answers.
Operator: Anthropic
robots.txt token: Claude-SearchBot
User-agent on the wire: not published by the operator
Category: Live retrieval / search index
What blocking it actually costs
You are removed from the index Claude's web search draws on.
How to block Claude-SearchBot
Add this to your robots.txt:
User-agent: Claude-SearchBot
Disallow: /
The token must appear on its own User-agent: line. A named group replaces the User-agent: * group rather than adding to it, so anything you also want disallowed for this crawler has to be repeated inside its group.
How to allow Claude-SearchBot
User-agent: Claude-SearchBot
Allow: /
An explicit allow is worth writing even when you have no blanket block: it documents the decision, and it survives someone later adding a restrictive User-agent: * rule without thinking about AI crawlers.
robots.txt is not the only thing that can block it
A permissive robots.txt does not mean Claude-SearchBot can reach you. WAF rules, Cloudflare's bot-management settings, rate limits and country blocks all sit in front of robots.txt and answer first. A site whose robots.txt welcomes Claude-SearchBot and whose edge returns 403 to it is blocked in every way that matters — and nothing in robots.txt will tell you so.
This is the gap the AI Crawler Access Checker was built to close: it reads robots.txt and sends a real request carrying the crawler's user-agent, so you see what the crawler sees.
Official documentation
Anthropic documents Claude-SearchBot at https://support.anthropic.com/en/articles/8896518.
Common questions
- What user-agent does Claude-SearchBot send?
Anthropic does not publish an exact user-agent string for Claude-SearchBot. Match on the
Claude-SearchBottoken in robots.txt rather than on a full string you found elsewhere.- How do I block Claude-SearchBot?
Add a group to robots.txt naming the token exactly:
User-agent: Claude-SearchBot Disallow: /The group must name
Claude-SearchBoton its own line. AUser-agent: *group does not combine with a named one — under RFC 9309 the most specific matching group replaces the wildcard entirely, it does not inherit from it.- What does blocking Claude-SearchBot cost me?
You are removed from the index Claude's web search draws on.
- Can I tell a real Claude-SearchBot request from a fake one?
Not reliably. Anthropic does not publish verified IP ranges for Claude-SearchBot, so the user-agent string is the only signal, and anyone can send it. Treat robots.txt as a statement of policy rather than as enforcement.
Is Claude-SearchBot blocked on your site right now?
Reading your own robots.txt only answers half of it — a firewall rule can block Claude-SearchBot while robots.txt says it is welcome. The checker tests both.
Check your site free