Safe Official docs AI & LLM Bots

Claude-SearchBot

Q: What is the official user-agent string for Claude-SearchBot?

The official user-agent string for Claude-SearchBot is: Claude-SearchBot . This is the exact string you must use in robots.txt, Nginx, Apache, or Cloudflare firewall rules to target this bot. User-agent matching in robots.txt is case-insensitive, but the string must be spelled correctly. You can verify that a request genuinely comes from Claude-SearchBot by performing a reverse-DNS lookup on the source IP - legitimate bots resolve back to their operator's domain.

Q: Is Claude-SearchBot safe?

Yes. Claude-SearchBot is a documented bot: Anthropic publishes a page that names it and explains what it does.

Q: How do I block Claude-SearchBot in robots.txt?

Add the following lines to your /robots.txt file: User-agent: Claude-SearchBot Disallow: / This instructs Claude-SearchBot not to crawl any path on your site. The Disallow: / directive covers the entire domain including subfolders. To only block specific sections, replace / with the path (e.g., Disallow: /blog/ ). Note: robots.txt is publicly readable - any bot or human can inspect it at yourdomain.com/robots.txt .

Q: How do I verify if Claude-SearchBot is crawling my site?

Search your web server access logs for the string Claude-SearchBot (case-insensitive grep: grep -i "Claude-SearchBot" /var/log/nginx/access.log ). You can also check Google Search Console → Coverage → Crawl Stats for Googlebot variants. For Claude-SearchBot specifically, filter by user-agent in your log analysis tool (GoAccess, AWStats, etc.).

Operated by Anthropic

Scout's quick take

Claude-SearchBot fetches pages so Anthropic's AI search can answer and cite them. Block it and you can drop out of those answers, so most sites keep it allowed.

# Block only if you really mean to
User-agent: Claude-SearchBot
Disallow: /

Run the free crawlability checker Build a full robots.txt

Quick Facts

User-Agent:: Claude-SearchBot
Category:: AI & LLM Bots
Operator:: Anthropic
Safety:: Safe
Blocking Impact:: Low - No SEO ranking impact
SEO Impact Score:: 2/10
Official docs:: support.claude.com

Confirmed by the operator

Anthropic names Claude-SearchBot on its own documentation page, linked above. The token, purpose and robots.txt behaviour on this profile come from that page, re-checked on October 19, 2026.

What is Claude-SearchBot?

Claude-SearchBot is Anthropic's search crawler. Anthropic says it "navigates the web to improve search result quality for users".

Anthropic separates search (Claude-SearchBot) from training (ClaudeBot). It identifies itself with the token Claude-SearchBot. Anthropic documents it at support.claude.com.

What happens if you block Claude-SearchBot?

Anthropic says disabling it "may reduce your site's visibility and accuracy in user search results" in Claude. No effect on Google or Bing.

Generally safe to allow; provides legitimate crawling value.

Claude-SearchBot in one paragraph

Claude-SearchBot is the Anthropic crawler that indexes pages for Claude's search features, and blocking it removes you from Claude search results. It is controlled independently of ClaudeBot, which collects training data, so you can allow one and block the other. For monitoring, see how do I monitor AI bot traffic to my website?

User-agent: Claude-SearchBot
Allow: /

User-agent: ClaudeBot
Disallow: /

Claude-SearchBot vs ClaudeBot vs Claude-User

Anthropic runs three bots and documents what blocking each one does (Anthropic crawler documentation, updated 7 April 2026). Claude-SearchBot is the one that decides whether Claude's search features can find and cite you.

Anthropic's three crawlers compared
Question	ClaudeBot	Claude-SearchBot	Claude-User
Purpose	Collects training data	Indexes pages for Claude search	Fetches a page a user asked about
Block it and...	Future training excludes your site	Claude search may not show or cite you	Claude cannot retrieve your page on request
Triggered by	Anthropic crawl schedule	Anthropic index schedule	A person in a chat
Crawl-delay	Supported	Supported	Not applicable (single fetch)
Evidence tier here	Official	Official	Official

Anthropic publishes its IP ranges at claude.com/crawling/bots.json but warns that blocking by IP may not work reliably; use robots.txt tokens.

Why Claude-SearchBot is the Anthropic bot to keep

Anthropic crawls far more than it refers. Cloudflare, 29 August 2025 measured 38,065 pages crawled for each visitor referred in July 2025, down from 286,930 in January. Most of that crawling is ClaudeBot training; the search and user bots are the part that can send people back.

Anthropic crawl-to-refer ratio, January vs July 2025.

ClaudeBot's share of all AI and search crawling also grew, from 6% to 9.9% over the year to July 2025.

Share of AI and search crawling by crawler.

Claude-SearchBot use cases

Use cases: what to do with this bot
If you are...	Recommended setting and why
You want Claude citations but not training	Allow Claude-SearchBot and Claude-User, block ClaudeBot.
You block every AI bot	Block all three by name; a wildcard block also works, but named groups are explicit.
Server load from Anthropic	Add Crawl-delay to ClaudeBot first; it is the high-volume one.

User-agent: Claude-SearchBot
User-agent: Claude-User
Allow: /

User-agent: ClaudeBot
Disallow: /

Verify with an AI crawler check and compare Anthropic with OpenAI's matching three tiers in ClaudeBot vs Claude-SearchBot and the Anthropic operator page.

Test Anthropic crawler access

AI crawler checker: tests 265 bots against your robots.txt in one scan.
AI crawler diagnostic: fetches a page as each AI bot and names the layer that blocks it.
robots.txt validator: shows allowed, blocked and partial status per bot.
robots.txt generator: builds a file with presets for search, agents and training.
batch URL checker: compares up to 20 sites side by side, with CSV export.
llms.txt generator: writes the file AI assistants read for a site summary.
schema markup generator: produces JSON-LD for eight common types.
GEO audit: scores a page for generative engine optimization.

How to block Claude-SearchBot with robots.txt

<code>User-agent: Claude-SearchBot</code> - Matching is case-insensitive. Robots.txt is fetched from the root of each subdomain separately.

Block completely (robots.txt)

User-agent: Claude-SearchBot
Disallow: /

Allow all (robots.txt)

User-agent: Claude-SearchBot
Allow: /

Block private only (robots.txt)

User-agent: Claude-SearchBot
Disallow: /private/
Disallow: /api/
Disallow: /admin/
Allow: /

Nginx server block

# Nginx: Hard-block Claude-SearchBot
if ($http_user_agent ~* "Claude\-SearchBot") {
    return 403 "Bot blocked";
}

Apache .htaccess

# Apache: Hard-block Claude-SearchBot
SetEnvIfNoCase User-Agent "Claude\-SearchBot" bad_bot
Order Allow,Deny
Allow from all
Deny from env=bad_bot

Meta robots tag

X-Robots-Tag header

X-Robots-Tag: noindex, nofollow

Is Claude-SearchBot safe to allow?

Yes. Claude-SearchBot is a documented bot: Anthropic publishes a page that names it and explains what it does.

Verify by reverse-DNS lookup: legitimate Claude-SearchBot requests resolve to anthropic's domain.

What does Claude-SearchBot do?

From Anthropic's own documentation.

Claude-SearchBot is Anthropic's search crawler.
Not used to train AI models, according to the operator
Anthropic says disabling it "may reduce your site's visibility and accuracy in user search results" in Claude. No effect on Google or Bing.

Claude-SearchBot in context

Claude-SearchBot is a retrieval crawler that feeds AI search answers operated by Anthropic. In plain terms, it fetches a page when a person asks an assistant or app to open it. Our database files it under AI and LLM crawlers and ranks it Tier 1, the small set whose absence you would notice in AI answers or search results. 14 of the 104 AI and LLM crawlers in our database share this tier.

Its safety rating is safe and its blocking impact is low. So the decision about Claude-SearchBot rests on what you want from Anthropic, not on its behaviour. How we rate safety and impact.

How site owners treat Claude-SearchBot

In our own study of robots.txt files across the Tranco top 10,000 sites (fetched October 20, 2026, 5,583 valid files), 359 files (6.4%) name Claude-SearchBot in a User-agent line, and 424 (7.6%) block it from the homepage. 207 of those blocks come from a group written for this crawler by name, and 217 come from a broad User-agent: * rule that catches it by accident. Larger sites are stricter: 13.6% of the top 1,000 block it, against 8.1% of the middle band and 6.2% of the tail.

Does it follow robots.txt?

Claude-SearchBot's operator says it follows robots.txt, so a correctly written Claude-SearchBot group is enough to control it.

Anthropic crawlers and close alternatives

Claude-SearchBot is one of 6 Anthropic crawlers in our database. A User-agent: Claude-SearchBot group controls Claude-SearchBot only; the other Anthropic tokens below need their own lines.

Claude-SearchBot: this crawler (Tier 1)
anthropic-ai: Anthropic AI (Deprecated), collects pages to train AI models (Tier 2)
Claude-Code: Claude Code Agent, fetches a page when a person asks an assistant or app to open it (Tier 2)
Claude-User: Claude User Agent, fetches a page when a person asks an assistant or app to open it (Tier 1)
Claude-Web: Claude Web (Deprecated), fetches a page when a person asks an assistant or app to open it (Tier 2)
ClaudeBot: Claude AI Training, collects pages to train AI models (Tier 1)

To give Claude-SearchBot the same answer as its siblings, stack User-agent: Claude-SearchBot with their lines above one set of rules; to treat Claude-SearchBot differently, give it its own group.

Other AI and LLM crawlers that do the same job (fetches a page when a person asks an assistant or app to open it) include ChatGPT Agent from OpenAI, ChatGPT Operator from OpenAI, ChatGPT-User from OpenAI, ChatGPT-User/2.0 from OpenAI, GrokAgent from xAI, muse- from Meta. Deciding about Claude-SearchBot is usually a decision about the whole group, so check how your file treats these too.

We first recorded Claude-SearchBot on March 17, 2026. Anthropic documents it on support.claude.com, and we recheck that page before each release.

Which rule Claude-SearchBot actually follows

Claude-SearchBot reads exactly one group in robots.txt, the most specific one that names Claude-SearchBot, and never combines rules across groups. This short file shows the trap:

User-agent: *
Disallow: /private/

User-agent: Claude-SearchBot
Disallow: /drafts/

Find the group. Claude-SearchBot looks for a group naming Claude-SearchBot. One exists, so it ignores User-agent: * completely.
Apply only that group. It is refused /drafts/ and nothing else.
The surprise. /private/ is open to Claude-SearchBot, because that rule lives in the * group it no longer reads. To keep it out of both, repeat Disallow: /private/ inside its own group.

Test yourself: does a rule under User-agent: * apply to Claude-SearchBot if the file also has a User-agent: Claude-SearchBot group?

No. Once a group names it, Claude-SearchBot reads only that group. Put every rule you want it to follow inside its own group.

Test yourself: will blocking Claude-SearchBot remove your pages from AI answers?

Often, yes. Claude-SearchBot is a retrieval crawler that feeds AI search answers, so pages it cannot fetch can drop out of the answers or results it supports.

Test yourself: is User-agent: claude-searchbot the same as User-agent: Claude-SearchBot?

Yes. RFC 9309 makes user-agent matching case-insensitive. Paths are a different story: Disallow: /Blog/ does not block /blog/.

Should you allow Claude-SearchBot? Decide by situation

Recommended setting for Claude-SearchBot by type of site
If you are...	Recommended setting
You publish content and want AI answers to cite it	Allow it. Claude-SearchBot fetches pages for answers, so blocking it can remove you from them.
You license content and want to stop AI training	Blocking it does not stop training, because Claude-SearchBot is a retrieval crawler that feeds AI search answers. Block the operator's training crawler instead.
You run an online shop	Allow it on product and category pages, which are the pages shoppers ask assistants about.
Your server is under load from bots	Rate-limit before blocking. It is rated safe in our database.

Check Claude-SearchBot on your own site

Open /robots.txt on your domain and search for Claude-SearchBot. If it is not named, it follows User-agent: *.
List the Disallow lines in the group Claude-SearchBot follows and test your key URLs against them; the longest match wins, and Allow wins a tie.
Look beyond the file. A firewall or bot manager can refuse Claude-SearchBot even when robots.txt allows it, and that never shows in the file.
Run our AI search visibility check to see how Claude-SearchBot and every other crawler we track are treated in one pass, including firewall refusals.

Common mistakes with Claude-SearchBot

The errors we see most often with Claude-SearchBot in the files and firewalls we test:

Blocking Claude-SearchBot while trying to stop AI training. Retrieval crawlers fetch pages so answers can cite them; blocking it can remove you from those answers without affecting training.
Letting a firewall or bot-fight mode refuse Claude-SearchBot while robots.txt allows it. The file looks right, but the crawler still gets a 403 or a challenge page.
Forgetting that once a User-agent: Claude-SearchBot group exists, Claude-SearchBot ignores every rule under User-agent: *.

All three hide inside a file that looks correct, so check Claude-SearchBot from outside after every change.

Spotting Claude-SearchBot in your logs

robots.txt says what Claude-SearchBot may do; your access logs show what it actually did.

Count requests

On a server with standard Nginx or Apache logs, this counts matching requests per day (adjust the log path for your host):

grep -iE "Claude-SearchBot" /var/log/nginx/access.log \
  | awk '{print $4}' | cut -d: -f1 | sort | uniq -c

And this shows which paths it requested most, which is the quickest way to see whether your Disallow lines are being respected:

grep -iE "Claude-SearchBot" /var/log/nginx/access.log \
  | awk '{print $7}' | sort | uniq -c | sort -rn | head -20

Check the requests are genuine

Anyone can send the Claude-SearchBot user-agent, so confirm the source before acting on a match:

Claude-SearchBot: compare each address with the ranges at claude.com/crawling/bots.json. A request claiming to be Claude-SearchBot from outside them is not genuine.

Frequently Asked Questions

What is the official user-agent string for Claude-SearchBot?

The official user-agent string for Claude-SearchBot is: Claude-SearchBot. This is the exact string you must use in robots.txt, Nginx, Apache, or Cloudflare firewall rules to target this bot. User-agent matching in robots.txt is case-insensitive, but the string must be spelled correctly. You can verify that a request genuinely comes from Claude-SearchBot by performing a reverse-DNS lookup on the source IP - legitimate bots resolve back to their operator's domain.

Is Claude-SearchBot safe?

Yes. Claude-SearchBot is a documented bot: Anthropic publishes a page that names it and explains what it does.

Will blocking Claude-SearchBot hurt my SEO?

Anthropic says disabling it "may reduce your site's visibility and accuracy in user search results" in Claude. No effect on Google or Bing.

How do I block Claude-SearchBot in robots.txt?

Add the following lines to your /robots.txt file:

User-agent: Claude-SearchBot
Disallow: /

This instructs Claude-SearchBot not to crawl any path on your site. The Disallow: / directive covers the entire domain including subfolders. To only block specific sections, replace / with the path (e.g., Disallow: /blog/). Note: robots.txt is publicly readable - any bot or human can inspect it at yourdomain.com/robots.txt.

Does Claude-SearchBot respect robots.txt?

Yes. Anthropic documents robots.txt control for all three of its bots.

How do I verify if Claude-SearchBot is crawling my site?

Search your web server access logs for the string Claude-SearchBot (case-insensitive grep: grep -i "Claude-SearchBot" /var/log/nginx/access.log). You can also check Google Search Console → Coverage → Crawl Stats for Googlebot variants. For Claude-SearchBot specifically, filter by user-agent in your log analysis tool (GoAccess, AWStats, etc.).

What is the crawl frequency of Claude-SearchBot?

Claude-SearchBot crawls at a moderate rate. If you notice excessive traffic in your logs, you can add a Crawl-delay directive:

User-agent: Claude-SearchBot
Crawl-delay: 10

(10 second delay between requests).

Can I block Claude-SearchBot from specific pages only?

Yes. Instead of a global Disallow: / you can restrict Claude-SearchBot to specific paths:

User-agent: Claude-SearchBot
Disallow: /private/
Disallow: /staging/
Allow: /

This allows Claude-SearchBot everywhere except the listed paths. Path matching in robots.txt uses prefix matching - Disallow: /private/ blocks /private/page.html but NOT /public/private/.

Does blocking Claude-SearchBot prevent AI training on my content?

Claude-SearchBot is not used for AI training, according to Anthropic. Anthropic separates search (Claude-SearchBot) from training (ClaudeBot).

Is there an alternative to robots.txt to opt out of Claude-SearchBot?

The opt-out Anthropic documents is robots.txt. A firewall, CDN or server rule that returns 403 for Claude-SearchBot enforces it. Per-bot meta tags and llms.txt are not opt-out mechanisms any major operator documents.

Can I block ClaudeBot but allow Claude-SearchBot?

Yes. They are separate robots.txt tokens. Anthropic documents that blocking ClaudeBot excludes your content from future training, while blocking Claude-SearchBot may stop Claude search from showing or citing your pages.

Claude-UserSafesame_operator
ClaudeBotSafesame_operator
AI2BotSafesame_category