Nobody has adopted ClaudeBot yet. Adopt ClaudeBot: your name goes on a plaque on this page for a year.
ClaudeBot's food bowl
the bowl, as bots see itThe bowl is empty. Last time, MJ12bot stole the Lightly Salted Packet Loss Popcorn, 14 days ago.
Identification
Its full user-agent string, exactly as it arrives at the gate:
Anthropic does not publish a way to verify ClaudeBot's traffic. Treat its user agent as a claim, not proof: anyone can send it.
Anthropic publishes no way to check it, so every visit filed here is taken at its word.
How to block ClaudeBot
Add these two lines to the robots.txt file at the root of your site. Well-behaved crawlers read it before they crawl, so the change applies from ClaudeBot's next visit. Nothing else on your site needs to change.
# Block ClaudeBot from the whole site User-agent: ClaudeBot Disallow: /
Anthropic also runs Claude-SearchBot (search) and Claude-User (user requests). Each has its own token.
Or let it visit but keep it away from part of the site:
# Let it in, but keep it out of one room User-agent: ClaudeBot Allow: / Disallow: /members/
Observed behaviour
Most active around 07:00. Before the coffee is made.
Requested 304 disallowed pages out of 2,750 requests. Read robots.txt 451 times.
Walked through the hidden /trap/ door.
Where it comes from
The networks ClaudeBot's visits came from:
Networks and countries come from the visitor's IP address, looked up in a local copy of the DB-IP database. The addresses themselves are never stored.
Keeper's field notes
Questions site owners ask
Does ClaudeBot respect robots.txt?
Mostly. It reads robots.txt, but it has fetched a disallowed page 304 times out of 2,750 requests observed here.
Will blocking ClaudeBot hurt my search rankings?
No. ClaudeBot isn't used by Google or Bing to rank pages. Blocking it only affects whether Anthropic collects your content.
How often does ClaudeBot visit?
Here, about 28 requests a day over the last week. Visits to your site depend on its size, how often it changes, and how many links point to it.