Assistant fetchers
MistralAI-User is a bot operated by Mistral that fetches single pages on demand for an AI assistant. MistralAI-User is Mistral's AI assistant bot that performs web browsing and data gathering tasks for users in Le Chat, including opening web pages and retrieving informat…. No IP range list or reverse-DNS convention is published, so a request carrying this user agent cannot be proven genuine and a robots.txt rule alone will not stop a forgery.
Request says
"MistralAI-User"
Checked against
Nothing published
Live check
No operator check exists for MistralAI-User. This still shows what the address really is.
Reference
| User agent | MistralAI-UserToken only: match on the substring. |
|---|---|
| Operator | Mistral |
| Purpose | Assistant fetchers |
| Respects robots.txt | No policy |
| Verification method | Claim onlyNone published, user agent only No IP range file and no reverse-DNS convention have been published for this agent. The user-agent string is the only signal, and any client can send it, so treat a match as a claim rather than proof. |
| Crawl pattern | Not published |
| Robots.txt tokens | MistralAI-UserMistralAI-User/1.0 |
| Operator documentation | None published |
MistralAI-User is Mistral's AI assistant bot that performs web browsing and data gathering tasks for users in Le Chat, including opening web pages and retrieving informat…
robots.txt
Paste one at the root of your domain. Rules are per token.
User-agent: MistralAI-User
User-agent: MistralAI-User/1.0
Disallow: /User-agent: MistralAI-User
User-agent: MistralAI-User/1.0
Allow: /User-agent: MistralAI-User
User-agent: MistralAI-User/1.0
Allow: /
Disallow: /account/
Disallow: /checkout/
Disallow: /searchEdit the Disallow paths to match your own URLs.
Blocking MistralAI-User means a person who asks about one of your URLs gets an error instead of a summary. That is a support and reputation trade-off, not a training one.
Build a file for every crawlerFAQ
MistralAI-User is a bot operated by Mistral that fetches single pages on demand for an AI assistant. MistralAI-User is Mistral's AI assistant bot that performs web browsing and data gathering tasks for users in Le Chat, including opening web pages and retrieving informat…. No IP range list or reverse-DNS convention is published, so a request carrying this user agent cannot be proven genuine and a robots.txt rule alone will not stop a forgery.
Not documented. No operator statement says whether MistralAI-User reads robots.txt, so add the rule but verify in your logs that the requests actually stop.
You cannot, at least not from the request itself. No IP range file and no reverse-DNS convention have been published for this agent. The user-agent string is the only signal, and any client can send it, so treat a match as a claim rather than proof. Compare the source IP against hosting and datacenter ranges instead, and rate limit anything that behaves like a crawler.
Add these user-agent tokens (MistralAI-User, MistralAI-User/1.0) to robots.txt with Disallow: /. If the crawler ignores robots.txt, match the user agent at your CDN or reverse proxy and return 403 there instead.
Blocking MistralAI-User means a person who asks about one of your URLs gets an error instead of a summary. That is a support and reputation trade-off, not a training one.