Skip to content

On demand · Mistral AI

MistralAI-User

Fetches a page when a Le Chat user asks about it. Mistral states these fetches are not used for training and that the agent respects robots.txt.

Operator
Mistral AI
Feeds
Le Chat
robots.txt token
MistralAI-User
Honours robots.txt
Honours robots.txt
Documentation
docs.mistral.ai

What it looks like in server logs

A representative user-agent string. Version numbers change; the MistralAI-User token does not. Paste your own log line into the user-agent checker to confirm a match.

user-agent
Mozilla/5.0 (compatible; MistralAI-User/1.0; +https://docs.mistral.ai/robots)

How to block MistralAI-User

Add this to the robots.txt at the root of your domain. Robots.txt is advisory: it works only on crawlers that choose to read it. This one is honours robots.txt according to its operator.

robots.txt
User-agent: MistralAI-User
Disallow: /

To block every user-triggered fetcher at once, or to block training while keeping AI search citations, use the robots.txt generator.

How to allow MistralAI-User while blocking others

A more specific User-agent group wins over a wildcard. Place this above any User-agent: * block that disallows paths, and MistralAI-User keeps full access.

robots.txt
User-agent: MistralAI-User
Allow: /

How to verify a genuine hit

The user-agent string is self-asserted: anyone can send it from a laptop, and scrapers routinely impersonate well-known crawlers to slip past filters aimed at unknown ones.

Mistral publishes the IP ranges its fetcher uses.