Claude-SearchBot (Anthropic)
AI search
What it is
Claude-SearchBot navigates the web to improve the quality and relevance of search results for Claude users. Anthropic says disabling it prevents your content from being indexed for search, which may reduce your site’s visibility and accuracy in user search results. Training is controlled separately through ClaudeBot.
Official documentation: support.claude.com · checked 13 Nov 2026
Claude-SearchBot user agent
Anthropic does not publish a full user agent string for Claude-SearchBot, only the token. Look for “Claude-SearchBot” in your logs and in robots.txt.
Official documentation: support.claude.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler · checked 13 Nov 2026
Block or allow Claude-SearchBot in robots.txt
Put these lines at the top of the robots.txt file in your site’s root (example.com/robots.txt). Each subdomain needs its own file.
User-agent: Claude-SearchBot
Disallow: /
User-agent: ClaudeBot
Disallow: /
Closes ClaudeBot. Claude-SearchBot, Claude-User stay under your general rules, so your pages can still appear in answers and results.
User-agent: Claude-SearchBot
Allow: /
# repeat here the Disallow lines of your User-agent: * group
If Claude-SearchBot is not named in robots.txt, it already follows your User-agent: * rules, so you don’t need anything. A group of its own replaces the * group for this bot entirely: if you add one, repeat your general Disallow lines in it.
- Anthropic asks you to add the rule for every subdomain you want to opt out.
Claude-SearchBot IP ranges
Official list: 14 ranges · published by the owner 20 Oct 2026 · we checked it 13 Nov 2026
Anthropic publishes one list for all its bots — ClaudeBot, Claude-User and Claude-SearchBot.
Check an IP from your logs
Show all 14
- 34.152.124.140/32
- 34.153.21.190/32
- 34.162.27.34/32
- 34.162.86.102/32
- 34.162.90.102/32
- 34.162.111.78/32
- 34.162.153.71/32
- 34.162.191.81/32
- 34.162.230.222/32
- 34.162.244.71/32
- 34.186.252.4/32
- 136.79.143.251/32
- 136.83.20.215/32
- 216.73.216.0/22
Does it respect robots.txt and Crawl-delay?
robots.txt: yes, Claude-SearchBot follows it according to its owner.
“Anthropic’s Bots respect “do not crawl” signals by honoring industry standard directives in robots.txt.” — Anthropic documentation
Crawl-delay: supported for Claude-SearchBot.
“we support the non-standard Crawl-delay extension to robots.txt” — Anthropic documentation
Should you block Claude-SearchBot?
Think twice. Claude-SearchBot is how Anthropic’s AI search finds your pages; block it and your site can drop out of its answers and links. If your concern is model training, block the training bot instead.
Check your site
See whether your robots.txt and firewall let Claude-SearchBot in — together with every other AI bot in this directory. Free, no sign-up.
Other Anthropic bots
Questions
What is the Claude-SearchBot user agent string?+
Anthropic does not publish a full user agent string for Claude-SearchBot. Match the token “Claude-SearchBot” instead.
How do I block Claude-SearchBot in robots.txt?+
Add a group for it to robots.txt in your site’s root: “User-agent: Claude-SearchBot” followed by “Disallow: /”.
What IP addresses does Claude-SearchBot use?+
Anthropic publishes 14 ranges at https://claude.com/crawling/bots.json. Requests that call themselves Claude-SearchBot from other addresses are most likely fake.
Does Claude-SearchBot respect robots.txt?+
robots.txt: yes, Claude-SearchBot follows it according to its owner.