LLMentions
AI crawlers · Claude-SearchBot

Claude-SearchBot: Anthropic's AI search indexer

Claude-SearchBot is Anthropic's AI search indexer. What it does, whether to allow it, robots.txt rules and how to verify real Claude-SearchBot traffic.

↓ Markdown for agents
Vendor
Anthropic
Type
AI search indexer
Runs JavaScript
No
IP ranges published
No

Claude-SearchBot is Anthropic's crawler that builds the search index behind Claude's web search. When someone asks a question, the answer is grounded in, and cites, pages this bot has indexed.

Should you allow Claude-SearchBot?

Allow it. If Claude-SearchBot can't crawl you, Claude's web search can't cite you, no matter how good your content is. Blocking it is the most common mechanical reason a brand is missing from AI answers.

robots.txt

To allow Claude-SearchBot everywhere:

text
User-agent: Claude-SearchBot
Allow: /

To block it:

text
User-agent: Claude-SearchBot
Disallow: /

Bots follow the most specific User-agent group that matches them. If you have a User-agent: Claude-SearchBot group, the rules under User-agent: * no longer apply to it. Matching on the token is case-insensitive.

Identifying Claude-SearchBot

Claude-SearchBot identifies itself with Claude-SearchBot in its User-Agent header. It does not run JavaScript: it reads the raw HTML only. Content your site adds with JavaScript is invisible to it.

Anthropic doesn't publish a machine-readable IP range list for Claude-SearchBot that we verify against, so treat the user agent alone as unverified. bots_report marks these hits as unverifiable rather than genuine.

Check your site

terminal
llmentions audit example.com            # is Claude-SearchBot allowed by robots.txt, and what does it see?
llmentions bots /var/log/nginx/access.log   # did Claude-SearchBot really visit, and is it genuine?

Or identify any user agent over REST (free): GET https://api.llmentions.com/v1/bots/lookup?ua=Claude-SearchBot.

Other Anthropic bots