Claude-SearchBot
Anthropic · Feeds a search index
Claude-SearchBot indexes pages to improve the relevance and accuracy of Claude's search answers. Anthropic says its bots do not try to bypass CAPTCHAs on the sites they crawl.
Fact sheet
- Operator
- Anthropic
- What it is for
- It crawls the web to build the index the assistant draws its answers from.
- Assistant it feeds
- Claude
- Counts towards the Parsigo score
- Yes. It feeds the index of one of the assistants we measure.
- Official documentation
- support.claude.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler
- Official IP ranges
- JSON list
If you block it
You ask for your pages to be left out of the index the assistant (Claude) draws its answers from.
Allow or block
A group of its own makes Claude-SearchBot ignore the “User-agent: *” rules. If you have Disallow lines there that should still apply to it, repeat them inside its group. To allow it, writing nothing is usually enough.
Allow
User-agent: Claude-SearchBot Allow: /
Block
User-agent: Claude-SearchBot Disallow: /
Test it on your site
We run the diagnostic on your site and show you whether Claude-SearchBot can get in, with the robots.txt line that decides it. Free, no sign-up.