MistralAI-Index
Mistral AI · AI search · robots.txt: Yes
Crawls the web automatically to index content for Mistral search, which helps answer questions in Mistral's Vibe assistant.
Block MistralAI-Index
User-agent: MistralAI-Index
Disallow: /Blocking MistralAI-Index keeps your pages out of the index behind Mistral search and Vibe’s answers. Mistral says content it crawls is not used for generative AI training of any kind; training has its own token, MistralAI-Training.
Allow MistralAI-Index
User-agent: MistralAI-Index
Allow: /An allow group only changes anything if a broader rule would block MistralAI-Index. Under the robots.txt standard (RFC 9309, section 2.2.1) a crawler follows the group that names it and uses the User-agent: * group only when no group does — so this group lets it in even if your * group says Disallow: /. Token matching is case-insensitive.
Put these lines in /robots.txt at the root of each host (each subdomain has its own file). robots.txt is a request to well-behaved crawlers, not access control.
Already have a robots.txt? Paste it into the robots.txt checker to see whether it blocks MistralAI-Index on a given path, and which line decides.
Facts
- Operator
- Mistral AI
- Purpose
- AI search index
- Obeys robots.txt
- Yes. Mistral documents MistralAI-Index as one of the robots.txt tokens it uses so webmasters can manage how their sites and content interact with its AI.
- In your server logs
- The user-agent string contains "compatible; MistralAI-Index/1.0;".
- How to verify it
- Match the IP against Mistral’s published MistralAI-Index IP list.
Published list: mistral.ai/mistralai-index-ips.json — 2 IPv4 ranges when we fetched it, list dated 19 Apr 2026. Always match against the live list; operators update them. To count real and fake MistralAI-Index requests in your own server log against this list, drop the log into the log reader.
What Mistral AI says
Quoted word for word from the operator's documentation.
“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.”
“To help webmasters manage how their sites and content interact with AI, Mistral uses specific robots.txt tags.”
“Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; MistralAI-Index/1.0;”
“All published IP addresses: MistralAI-Index IP addresses”
Sources
- Mistral Docs: Mistral crawlers — fetched and checked 2026-09-24
- Mistral: MistralAI-Index IP addresses (mistralai-index-ips.json) — fetched and checked 2026-09-24