← AI crawler directory
AI answer
Claude-SearchBot
AnthropicHonours robots.txt
Crawls the web to improve the quality of Claude's search-grounded answers. Blocking limits whether Claude fetches your pages when answering search-grounded queries.
User-agent string
Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko); compatible; Claude-SearchBot/1.0
How to verify it
Anthropic publishes crawler IPs at claude.com/crawling/bots.json.
What blocking costs
Blocking limits whether Claude fetches your pages when answering search-grounded queries.
robots.txt rule
# Block Claude-SearchBot
User-agent: Claude-SearchBot
Disallow: /
# Allow everything else
User-agent: *
Allow: /Robots.txt is enough
Anthropic documents Claude-SearchBot as honouring robots.txt. Verify with your logs after deploying — a spoofed agent will keep coming.
Generate a full robots.txt
Pick which AI crawlers to allow or block across all 42 agents and copy the file out.
Open the generator →Other Anthropic agents