What MistralAI-Index does
MistralAI-Index is Mistral AI's crawler for automated crawling of the web for indexing purposes only, feeding the index behind Mistral's search feature. Mistral states that content crawled by MistralAI-Index is not used for generative AI training of any kind. It identifies itself with a user agent containing MistralAI-Index/1.0 and a link to Mistral's robots documentation, and it can be controlled through standard robots.txt directives. It is distinct from MistralAI-User, Mistral's agent for individual user-triggered actions.
How to control MistralAI-Index
Target MistralAI-Index in your robots.txt with the MistralAI-Index token. Rules apply per bot, so you can allow this one while blocking others, or the reverse.
Allow MistralAI-Index
User-agent: MistralAI-Index
Allow: /Block MistralAI-Index
User-agent: MistralAI-Index
Disallow: /Mistral publishes the full list of MistralAI-Index crawler IP addresses at mistral.ai/mistralai-index-ips.json, so requests claiming this user agent can be checked against that list.
How to identify MistralAI-Index
Temso identifies MistralAI-Indextraffic by matching the request's User-Agent header against this pattern. User-agent strings can be spoofed, so treat a match as an indication, not proof.
MistralAI-IndexMistralAI-Index FAQ
What is MistralAI-Index?
MistralAI-Index is Mistral AI's web crawler, used for automated crawling and indexing to support Mistral's search feature. Mistral states that content it crawls is used for indexing only and not for generative AI training of any kind.
How do I block MistralAI-Index?
Add a robots.txt group with "User-agent: MistralAI-Index" followed by "Disallow: /" (or narrower Disallow rules for specific paths). Mistral's documentation says the crawler is managed through standard robots.txt directives, and you can verify its traffic against the IP list Mistral publishes.
About AI Search Crawlers
Crawlers that build the retrieval indexes behind AI search products like ChatGPT search and Perplexity. They decide which pages can be cited as sources.
Blocking these keeps your content out of the source index: AI search products can't cite pages they can't crawl.
