AI crawlers·Mistral
MistralAI-User
Mistral’s fetcher for users of Vibe, its assistant. When someone asks Vibe a question, it may visit a page to help answer and link to the source. Mistral says it does not crawl the web automatically or collect training data.
- Operator
- Mistral
- robots.txt token
MistralAI-User- Follows robots.txt
- Yes
- IP ranges
- Published
- In Spreelytics
- AI answers tab
- Source
- Mistral’s documentation
What user agent does MistralAI-User use?
Mistral publishes this user agent string for MistralAI-User.
Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; MistralAI-User/1.0; +https://docs.mistral.ai/robots)How do I block MistralAI-User?
Mistral lists MistralAI-User among its robots.txt tags, and says the tag decides which sites these user requests can reach.
Add this to the robots.txt file at the root of your site:
User-agent: MistralAI-User
Disallow: /How do I check that a MistralAI-User visit is real?
Anyone can put a crawler’s name in a user agent, so the name alone proves nothing.
Mistral publishes the IP addresses MistralAI-User makes requests from, as JSON.
Spreelytics runs this check for you. Every crawl that claims to be MistralAI-User is compared with the IP ranges Mistral publishes, refreshed every 12 hours, and one from outside them counts as spoofed.
How do I see MistralAI-User visits on my site?
Your server’s access logs record the user agent of each request, so you can search them for “MistralAI-User”.
Or add the Spreelytics server middleware, @spreelytics/ai-crawl. It recognises MistralAI-User by its user agent and counts each visit on the Bots page under AI answers, as Vibe, apart from your visitor numbers.
Sources: docs.mistral.ai/robots
See your own numbers today.
Free up to 100k events a month · no credit card