AI crawler · Mistral AI

MistralAI-Index: what it is and how to block it

MistralAI-Index crawls the web to build the search index Mistral's assistant uses to answer questions. Mistral says the content isn't used for AI training.

BrandVector Editorial · Last verified Oct 8, 2026

Operator
Mistral AI
Type
Search
robots.txt token
MistralAI-Index
Follows robots.txt
Mistral AI doesn't say
IP ranges
Published
Blocked by name
0.2% of top sites

What is MistralAI-Index?

MistralAI-Index is Mistral AI's search crawler: it indexes pages for search results. In Mistral AI's words:

“MistralAI-Index is for automated crawling of the web for indexing purposes only. It indexes content for Mistral search, which helps answer user questions in Vibe.”

“Content crawled by MistralAI-Index is not used for generative AI training of any kind.”

MistralAI-Index user agent string

Mistral AI documents this user agent string for MistralAI-Index:

Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; MistralAI-Index/1.0; +https://docs.mistral.ai/robots)

In robots.txt, use the token MistralAI-Index, not the full string. Crawlers match on the token, and version numbers in the full string can change.

How many websites block MistralAI-Index?

In our Oct 8, 2026 check of 817 of the most-visited websites, 0.2% block MistralAI-Index by name for their whole site (2 sites).

robots.txt rule for MistralAI-IndexSitesShare
Blocks the whole site by name20.2%
Blocks part of the site by name30.4%
Names it but doesn't block it00.0%
Blocked only by a catch-all (*) rule374.5%

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-Index in robots.txt

Add this group to the robots.txt file at the root of your domain to block MistralAI-Index from your whole site:

User-agent: MistralAI-Index
Disallow: /

To block only part of your site, list those paths instead:

User-agent: MistralAI-Index
Disallow: /private/

A group that names MistralAI-Index replaces your User-agent: * rules for it entirely (RFC 9309). If your catch-all group blocks paths that MistralAI-Index should also stay out of, repeat them in its group. To let MistralAI-Index in while a catch-all rule blocks others:

User-agent: *
Disallow: /

User-agent: MistralAI-Index
Allow: /

Mistral AI doesn't say whether MistralAI-Index follows robots.txt, so a robots.txt block is a request it may not honor.

What happens if you block MistralAI-Index?

Mistral AI doesn't document what blocking MistralAI-Index changes.

How to verify requests from MistralAI-Index

Mistral AI publishes the IP addresses MistralAI-Index uses. Check a request's IP address against that list before trusting its user agent, which any client can fake.

See every AI crawler and how often top sites block it

Sources

  1. Mistral AI: Robots
  2. RFC 9309: Robots Exclusion Protocol
  3. Chrome UX Report top 1,000 origins (global), August 2026

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.