MistralAI-User
Mistral · User-action fetcher
What it does
MistralAI-User fetches a page because a user asked about that specific link. Fetches a page on behalf of a Le Chat user.
It does not execute JavaScript. Whatever your server returns in the initial HTML response is the entire page as far as MistralAI-User is concerned — if your content is rendered client-side, this crawler reads an empty container.
Should you block MistralAI-User?
Blocking it means that when someone pastes your URL and asks what it says, the assistant cannot read it and says so. This is the most direct visibility loss of the three.
A Le Chat user who shares your URL gets a fetch failure instead of your content. As with other user-action fetchers, the loss is immediate and visible to a person.
To allow it
User-agent: MistralAI-User
Allow: /To block it
User-agent: MistralAI-User
Disallow: /Put the rule in your robots.txt at the site root. A group that names MistralAI-User explicitly takes precedence over your User-agent: * group, so naming it is how you make your intent survive later edits to the wildcard rules.
Verifying a real MistralAI-User request
This is a user-triggered fetcher, so requests arrive individually in response to a human action rather than as a crawl. Check source IPs against Mistral's published infrastructure rather than trusting the string.
The mistake people make
Omitting it from an allow list built around the American AI companies. European users reaching your content through a European assistant are still users.
Can MistralAI-User reach your site?
The free scan parses your robots.txt, evaluates every AI crawler against it, and tells you how much of a page MistralAI-User would actually come away with.
Run the free scan