MistralAI-User: Mistral's fetch for a person
MistralAI-User belongs to Mistral. It opens a page at the moment a person asks an assistant about it. It doesn't crawl on its own. When it is turned away, the assistant can't read your page while answering, so it answers from memory or from other sites.
| Operator | Mistral |
|---|---|
| Used for | Mistral's assistant |
| Type | Fetch for a person |
| 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) |
| Published IP ranges | https://mistral.ai/mistralai-user-ips.json |
| Official documentation | docs.mistral.ai/robots |
Mistral says it is not used for automatic crawling or for training. Mistral documents two more agents: MistralAI-Index (search indexing) and MistralAI-Training (training data).
Allow or block MistralAI-User in robots.txt
To block it on the whole site:
User-agent: MistralAI-User
Disallow: /To allow it explicitly (useful when a rule for all bots would block it):
User-agent: MistralAI-User
Allow: /Mistral describes it as a robots.txt tag that governs which sites these user requests can be made to.
robots.txt is a request, not a wall. A CDN or firewall rule can turn a bot away even when robots.txt allows it, and nothing in the file will show that.
The free check requests your home page as a browser and as AI bots, reads your robots.txt and shows what gets blocked. No sign-up.
Check my siteIs it really MistralAI-User?
Anyone can send a request with this bot's name. Mistral publishes the IP ranges its requests come from, so a request that carries the name from another address is an impostor. You can check a request's IP address against that list.
See MistralAI-User on your own site
MistralAI-User doesn't run JavaScript, so analytics scripts never record it. AI Visibility in PageLens reads it from your server or CDN and shows which pages it requested, when, and which requests ended in a 404.