MistralAI-Index user agent and robots.txt rules

MistralAI-Index crawls pages for Mistral’s search index, which helps answer questions in Vibe. Mistral says that content is not used for AI training.

AI search Not documented Mistral AI

User agent

As documented by Mistral AI. Version numbers change; match on the token.

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

robots.txt rules for MistralAI-Index

Paste one block into the robots.txt at the root of your domain. Changes can take up to a day to be read.

Block MistralAI-Index

Disallows every path for MistralAI-Index. That keeps your pages out of Mistral AI’s AI search index, so its answers can’t cite them.

robots.txt
User-agent: MistralAI-Index
Disallow: /

Allow MistralAI-Index

Lets MistralAI-Index fetch every path, whatever “User-agent: *” says.

robots.txt
User-agent: MistralAI-Index
Allow: /

Good to know

Mistral’s page doesn’t describe how it reads robots.txt.

MistralAI-Index FAQ

What is MistralAI-Index?

MistralAI-Index crawls pages for Mistral’s search index, which helps answer questions in Vibe. Mistral says that content is not used for AI training.

How do I block MistralAI-Index?

Add “User-agent: MistralAI-Index” and “Disallow: /” to your robots.txt. That keeps your pages out of Mistral AI’s AI search index, so its answers can’t cite them.

Does MistralAI-Index respect robots.txt?

Mistral AI’s documentation doesn’t say. Block it in robots.txt and, if needed, at your firewall by its published IPs.

What is the MistralAI-Index user agent?

Mistral AI documents it as “Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; MistralAI-Index/1.0; +https://docs.mistral.ai/robots)”. Version numbers change, so match on “MistralAI-Index”.

How can I verify MistralAI-Index requests?

Match the request IP against Mistral AI’s published list (https://mistral.ai/mistralai-index-ips.json). The user agent alone can be faked.

Source: docs.mistral.ai, checked Nov 17, 2026. AI Crawler Directory

Files are the start. Answers are the result.

Your buyers’ questions on eight AI engines, on your schedule, with history. Free for 7 days.