Should you block MistralAI-Index? Mistral's search crawler
MistralAI-Index is operated by Mistral. It crawls the web automatically to build the index behind Mistral search, which Vibe uses to answer questions. Mistral says nothing it collects is used for AI training.
Who should block MistralAI-Index, and who should not?
Leave it open if you want Vibe to find your pages through Mistral search; disallow it if you would rather stay out of that index. It is not a training opt-out, because Mistral says this crawler feeds no training; that job belongs to MistralAI-Training. It also does not stop MistralAI-User, which fetches a page when a Vibe user's question needs it. The IP file is small enough to check by hand: two published addresses, so a request outside them that claims this name is not Mistral's.
The verified facts
| User-agent token | MistralAI-Index/1.0 |
|---|---|
| Full user agent in logs | Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; MistralAI-Index/1.0; +https://docs.mistral.ai/robots) |
| Operator | Mistral |
| Purpose | Search and AI-search indexers |
| Honors robots.txt | Yes, per the operator's documentation. |
| Published IP ranges | mistral.ai/mistralai-index-ips.json |
What does Mistral’s documentation add?
- Mistral says MistralAI-Index crawls for indexing purposes only, and that content it crawls is not used for generative AI training of any kind.
- On 2026-09-26 its IP file listed two single IPv4 addresses (/32) in a file dated 2026-04-19. None of them appears in the MistralAI-User file, so an address tells you which Mistral agent sent a request.
How do you block MistralAI-Index?
Add this to your robots.txt:
User-agent: MistralAI-Index
Disallow: /Once you give a crawler its own group, it stops reading your User-agent: * rules, so run the whole file through the AI crawler robots.txt tester before you deploy it.
How do you tell a real MistralAI-Index request from a fake one?
A user-agent match proves nothing, since any client can send MistralAI-Index/1.0. Check the IP against the published range file above, re-fetched on a schedule. A request that fails is not Mistral. The log verification guide has a script for the IP check and a worked reverse-DNS example, or paste the IP into the AI crawler IP verifier, which runs these checks against Mistral’s current data.
What does blocking MistralAI-Index cost you?
Your pages leave the Mistral search index that Vibe draws on to answer questions.
What else does Mistral document?
Mistral also documents MistralAI-User and MistralAI-Training, each with its own robots.txt token. How Mistral’s crawlers fit together.
Which crawlers in the same group should you decide on at the same time?
A robots.txt group for MistralAI-Index does nothing to crawlers with other tokens. In the same group, the directory also covers LinerBot (Liner), OAI-SearchBot (OpenAI), Claude-SearchBot (Anthropic), Googlebot (Google), Bingbot (Microsoft) and Applebot (Apple), each with its own token and its own documented cost of blocking.