Mistral AI · AI answers
MistralAI-User
Visits a page when someone asks Mistral's assistant Vibe a question, and may link to it as a source. Mistral says it does not crawl automatically and is not used to collect training data.
- robots.txt name
MistralAI-User- User agent
Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; MistralAI-User/1.0; +https://docs.mistral.ai/robots)- Category
- AI answers: Fetch a page when someone asks an assistant about it.
- Follows robots.txt
- Yes
- Official documentation
- https://docs.mistral.ai/robots
- Published IP ranges
- https://mistral.ai/mistralai-user-ips.json
Checked against the official documentation on October 17, 2026.
Block or allow it in robots.txt
Add these lines to the robots.txt file at the root of your domain. To block it everywhere:
User-agent: MistralAI-User
Disallow: /
To allow it everywhere except one folder:
User-agent: MistralAI-User
Disallow: /private/
Is it really this bot?
Anyone can copy a user agent. To be sure a request comes from Mistral AI, compare its IP address with the ranges the company publishes.
Other bots from Mistral AI
- MistralAI-Index · Search indexes
- MistralAI-Training · Training crawlers
See which AI crawlers read your site
Statsdot keeps bots out of your visitors and, with AI crawler tracking, shows which crawlers read your pages and which pages they request. No cookies, no personal data.