MistralAI-User

MistralAI-User fetches a page live when someone asks the AI platform about it. Most operators use a separate user agent for each job, so you can usually allow or block one without affecting the others.

Page fetches requested by AI platform users. A verified request establishes a page read, not a citation or a human visit.

Requests from MistralAI-User carry this token in their user agent string. Match the token rather than a full string, which changes as Mistral AI updates versions.

To block MistralAI-User, add this to the robots.txt at the root of your site:

Blocking it stops the assistant reading your page when a user asks for it, so the answer is built from other sources. Operators can treat user-requested fetches differently from automatic crawling; check the operator's documentation for how it applies robots.txt.

To allow it explicitly, for example after a broader rule blocks other crawlers:

Check what your robots.txt allows for MistralAI-User and the other AI crawlers in this directory.

Mistral AI publishes the IP addresses MistralAI-User uses. A request that claims to be MistralAI-User from any other address is not genuine.

• mistral.ai/mistralai-user-ips.json

SurfacedBy's AI traffic tracking recognizes MistralAI-User in the user agent and checks each request against Mistral AI's published addresses. Only requests that pass count as crawls; the rest are shown separately.

Details on this page come from Mistral AI's own documentation: docs.mistral.ai/robots.

• MistralAI-IndexSearch indexing
• MistralAI-TrainingTraining