MistralAI-Index: Mistral's AI search crawler
Mistral's crawler for indexing only: it builds Mistral search, which answers questions in Vibe.
- Free, no account.
- A few seconds.
- Nothing is stored.
MistralAI-Index at a glance
Everything Mistral documents about it, with links to the source.
- Operator
- Mistral
- Type
- AI search and answers
- Used for
- Mistral search, which answers questions in Vibe
- Obeys robots.txt
- Yes. Mistral documents that MistralAI-Index follows robots.txt, so a rule for its token is honoured.
- robots.txt token
MistralAI-Index- User-agent string
Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; MistralAI-Index/1.0; +https://docs.mistral.ai/robots)
- IP addresses
- mistral.ai/mistralai-index-ips.json
- Documentation
- docs.mistral.ai/robots
How to block MistralAI-Index
Fetches the pages AI answers cite and link to. Blocking it keeps your pages out of those answers: no citation, no link.
Block the whole site
Add this group to robots.txt at the root of your site.
User-agent: MistralAI-Index Disallow: /
Block only some paths
List the paths; everything else stays open to MistralAI-Index.
User-agent: MistralAI-Index Disallow: /private/ Disallow: /drafts/
How to verify MistralAI-Index
Anyone can send a crawler's user-agent string. Where the request comes from is what proves it.
- 1
Find requests whose user agent contains "MistralAI-Index" in your server or CDN logs.
- 2
Check each source IP against Mistral's published list (mistral.ai/mistralai-index-ips.json). A request from outside it is not MistralAI-Index, whatever it says.
- 3
Block what fails the check at the firewall. A robots.txt rule only reaches crawlers that choose to read it.
Other crawlers from Mistral
Each has its own token, and blocking one leaves the others untouched.
Frequently asked questions
Mistral's crawler for indexing only: it builds Mistral search, which answers questions in Vibe. Mistral says content it crawls is not used for generative AI training of any kind.
Yes. Mistral documents that MistralAI-Index follows robots.txt, so a rule for its token is honoured.
Add a group for its token to robots.txt at the root of your site: "User-agent: MistralAI-Index" followed by "Disallow: /". To close only part of the site, list those paths instead of "/". To enforce the block rather than request it, deny the IP addresses Mistral publishes at your firewall.
Mistral's AI answers stop finding your pages through it, so they cannot cite or link to you. If you want to keep your content out of training but stay in answers, block Mistral's training token instead and leave MistralAI-Index allowed.
Checked against Mistral's documentation on 29 September 2026.
Next: see whether AI recommends you
Letting the right crawlers in is the first step. AskWatch shows what ChatGPT, Perplexity, Gemini and Google AI answer when buyers ask about your category, and who they name.
- Free, no credit card.
- Report in minutes, link sent to your email.