MistralAI-User

Mistral AI · User-requested fetch

MistralAI-User visits a web page when a user asks Mistral's assistant a question, and the answer may link to the source. Mistral says it is not used for automatic crawling or for generative AI training, and that the MistralAI-User robots.txt token governs which sites these requests can be made to.

What it does

Mistral says MistralAI-User is for user actions in its assistant: when a user asks a question, it may visit a web page to help answer and include a link to the source in its response. It is not used for crawling the web automatically or for generative AI training.

Mistral uses separate tokens for its other agents: MistralAI-Index for search indexing and MistralAI-Training for training datasets. Blocking MistralAI-User affects only live fetches on a user's behalf.

robots.txt token

MistralAI-User

User-agent string

Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; MistralAI-User/1.0; +https://docs.mistral.ai/robots)

How to allow it

User-agent: MistralAI-User
Allow: /

How to block it

User-agent: MistralAI-User
Disallow: /

How to verify real visits

Mistral publishes the IP addresses MistralAI-User uses. Match the source IP of a request against that list rather than trusting the user agent.

Check if your site lets it in →