MistralAI-User

Fetches a page when someone asks Mistral's assistant about it, and links the page as a source. Mistral says it doesn't crawl automatically or collect training data.

What happens if you block it

Mistral's assistant can't open your pages on request, so it won't cite them.

Our take

Allow it if you want to be cited in Mistral's assistant.

robots.txt

To block it:

User-agent: MistralAI-User
Disallow: /

To allow it explicitly (useful when a wider rule blocks other bots):

User-agent: MistralAI-User
Allow: /

The operator's own words

When users ask Vibe a question, it may visit a web page to help answer and include a link to the source in its response. MistralAI-User governs which sites these user requests can be made to.Mistral AI documentation, checked 2026-11-04

robots.txt allows it, but is it really getting through?

A firewall or CDN rule can reject MistralAI-User even when robots.txt welcomes it, and nothing in your CMS shows it. Our check sends a live request as MistralAI-User alongside a normal browser and a Googlebot control, so a bot-verification rule isn't mistaken for a block.

Other Mistral AI agents