AI crawler · Mistral AI
MistralAI-User: what it is and how to block it
MistralAI-User is the agent Mistral's assistant uses to visit a page when a user asks a question, so it can cite the source in its answer.
BrandVector Editorial · Last verified Oct 8, 2026
- Operator
- Mistral AI
- Type
- User-triggered
- robots.txt token
MistralAI-User- Follows robots.txt
- Yes, per Mistral AI
- IP ranges
- Published
- Blocked by name
- 4.0% of top sites
What is MistralAI-User?
MistralAI-User is Mistral AI's user-triggered crawler: it fetches a page when a user asks an AI assistant to. In Mistral AI's words:
“MistralAI-User is for user actions in Vibe. 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.”
“It is not used for crawling the web in any automatic fashion, nor to crawl content for generative AI training.”
MistralAI-User user agent string
Mistral AI documents 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)
In robots.txt, use the token MistralAI-User, not the full string. Crawlers match on the token, and version numbers in the full string can change.
How many websites block MistralAI-User?
In our Oct 8, 2026 check of 817 of the most-visited websites, 4.0% block MistralAI-User by name for their whole site (33 sites).
| robots.txt rule for MistralAI-User | Sites | Share |
|---|---|---|
| Blocks the whole site by name | 33 | 4.0% |
| Blocks part of the site by name | 7 | 0.9% |
| Names it but doesn't block it | 1 | 0.1% |
| Blocked only by a catch-all (*) rule | 35 | 4.3% |
For comparison, 0.1% of the same sites block Googlebot by name. The sites are the top 1,000 origins in the Chrome UX Report for August 2026; see how we measured.
How to block MistralAI-User in robots.txt
Add this group to the robots.txt file at the root of your domain to block MistralAI-User from your whole site:
User-agent: MistralAI-User Disallow: /
To block only part of your site, list those paths instead:
User-agent: MistralAI-User Disallow: /private/
A group that names MistralAI-User replaces your User-agent: * rules for it entirely (RFC 9309). If your catch-all group blocks paths that MistralAI-User should also stay out of, repeat them in its group. To let MistralAI-User in while a catch-all rule blocks others:
User-agent: * Disallow: / User-agent: MistralAI-User Allow: /
“MistralAI-User governs which sites these user requests can be made to.”
What happens if you block MistralAI-User?
Mistral AI doesn't document what blocking MistralAI-User changes.
How to verify requests from MistralAI-User
Mistral AI publishes the IP addresses MistralAI-User uses. Check a request's IP address against that list before trusting its user agent, which any client can fake.
Other Mistral AI crawlers
- MistralAI-Training · AI training
- MistralAI-Index · Search
See every AI crawler and how often top sites block it
Sources
Rather have an expert do it?
Tell us about your site and goals, and we'll match you with an AI visibility (GEO) specialist. Free, no obligation.