MistralAI-User
Mistral AI operates MistralAI-User, which may fetch a web page when a user asks Vibe a question and link the source in the answer. Mistral says it does not crawl automatically or gather training data. Its robots.txt token is MistralAI-User; per-bot robots.txt compliance is undocumented. Mistral publishes IP ranges at mistral.ai/mistralai-user-ips.json and documents no reverse-DNS method.
Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; MistralAI-User/1.0; +https://docs.mistral.ai/robots)What MistralAI-User does
The user-agent string reads Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; MistralAI-User/1.0; +https://docs.mistral.ai/robots). Mistral states the agent is not used for crawling the web in any automatic fashion, so the operator ties each request to a user action in Vibe rather than to a scheduled crawl. Mistral says the fetch happens so Vibe can answer the question and include a link to the source in its response. The docs describe the token as governing which sites these user requests can be made to.
Allowing MistralAI-User lets Vibe read your page on a user's behalf and cite it as a source. Blocking it withdraws your pages from those on-demand fetches, so Vibe would no longer pull the page or link to it when a user asks. Mistral states this agent is not used for crawling the web in any automatic fashion, nor to crawl content for generative AI training, so a block here has no stated effect on training data collection. The docs page intro says Mistral uses specific robots.txt tags so webmasters can manage access, but no separate sentence confirms that MistralAI-User itself obeys robots.txt.
Mistral publishes an IP list at https://mistral.ai/mistralai-user-ips.json. The file is a JSON object with a creationTime field and a prefixes array of objects keyed ipv4Prefix. Mistral does not document crawl rate, JavaScript execution or reverse DNS for this agent, so the IP list is the one verification path Mistral gives.
Operator note. The documentation's introduction states that Mistral "uses specific robots.txt tags" to let webmasters manage access; there is no separate per-bot sentence about robots.txt compliance for this token, and no crawl-rate, JavaScript-execution, or reverse-DNS details are documented. The published IP file is dated 2025-02-19 and lists individual IPv4 addresses (/32 prefixes) only, with no IPv6 entries.
Controlling MistralAI-User with robots.txt
Use the token MistralAI-User in robots.txt. Mistral AI's documentation does not state whether this bot honors robots.txt.
User-agent: MistralAI-User
Disallow: /User-agent: MistralAI-User
Allow: /Verifying a request is really MistralAI-User
Anyone can put MistralAI-User in a User-Agent header. Mistral publishes the IP ranges for this crawler at https://mistral.ai/mistralai-user-ips.json. No reverse-DNS method is documented.
Mistral AI publishes a machine-readable list. Our probe read it on 2026-09-06; the file's own creation time was 2025-02-19.
- Prefixes
- 4
- IPv4
- 4
- IPv6
- 0
First entries at fetch time: 20.240.160.161/32, 20.240.160.1/32, 20.240.194.83/32
SHA-256 of the fetched body: 6226c5829c7edb91995769a9f3f0a52b686b4a18cc5a8d6d92479d2908f793f6
Common questions
Should I block MistralAI-User?
Blocking it stops Vibe from fetching your pages when a user asks a question and from linking to your site as a source. Mistral says the agent does no automatic crawling and no training data collection, so blocking it does not affect either of those. Mistral documents the MistralAI-User robots.txt token, though it does not state per-bot compliance.
Does MistralAI-User obey robots.txt?
Mistral's docs page says the company uses specific robots.txt tags so webmasters can manage access, and lists MistralAI-User as one of those tokens. There is no separate per-bot statement of robots.txt compliance for MistralAI-User, so compliance for this token is undocumented.
How do I verify MistralAI-User?
Compare the requesting IP against the list Mistral publishes at https://mistral.ai/mistralai-user-ips.json. The file contains a prefixes array of ipv4Prefix values. Mistral documents no reverse-DNS check for this agent.
Sources
Every fact on this page was checked against Mistral AI's own documentation, listed below, and re-checked by a second reviewer before publication. Reviewed September 2026.
Related crawlers
This registry documents how operators describe their own bots so site owners can identify and control them. It does not publish third-party IP lists or guess at undocumented behaviour. To see how your own site responds to automated visitors, the bot detection scanner reads a URL's live response and names the protection it finds.