AI crawler index
What is MistralAI-User?
MistralAI-User is Mistral AI's fetcher for pages users ask about. Visits a page when a user asks Mistral's assistant a question that needs it, and cites the source.
At a glance
| Operator | Mistral AI |
|---|---|
| Purpose | User-triggered fetch |
| User agent | Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; MistralAI-User/1.0; +https://docs.mistral.ai/robots) |
| Obeys robots.txt | Yes, according to the operator |
| Published IP ranges | https://mistral.ai/mistralai-user-ips.json |
| How to verify it | Mistral publishes its IP ranges as JSON; match the source IP against them. |
| Official documentation | https://docs.mistral.ai/robots |
Should you block MistralAI-User?
It visits a page only when a user asks the assistant something that needs it. Blocking it stops the assistant from reading your page in those moments, which costs you citations; and because a person starts each request, robots.txt may not stop it.
Mistral says it is not used for automatic crawling or AI training. It also documents MistralAI-Index for search and MistralAI-Training for training.
How to block or allow MistralAI-User in robots.txt
Block it everywhere:
User-agent: MistralAI-User
Disallow: /Allow it everywhere:
User-agent: MistralAI-User
Allow: /Rules are matched by the token on the User-agent line. Test the result with the robots.txt tester before you publish it.
Check your own site
The AI crawler checker tells you which AI crawlers your robots.txt lets in, and the log file analyzer shows how often each one actually visits. For the bigger picture, see what AI crawlers are and the full AI crawler index.
FAQ
MistralAI-User questions
Start tracking your brand in AI search today
Monitor how AI engines cite your brand, track keyword positions, and benchmark against competitors, all in one platform.