MistralAI-User
Mistral AI's agent for visiting a page when a user asks Vibe a question, with a link to the source. It does not crawl automatically or collect training data.
| Operator | Mistral AI |
|---|---|
| Purpose | Browsing — Vibe (Mistral AI) |
| robots.txt token | MistralAI-User |
| User-Agent | Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; MistralAI-User/1.0; +https://docs.mistral.ai/robots) |
| Obeys robots.txt | Not stated by the publisher |
| Official IP ranges | https://mistral.ai/mistralai-user-ips.json — 4 ranges, list dated 2025-02-19 |
| Reverse DNS | Not documented |
| Official documentation | https://docs.mistral.ai/robots |
Live activity of MistralAI-User
No visit from MistralAI-User recorded on iabig.com over the last 30 days.
Last updated: 2026-10-25 14:07:01 UTC. See the Observatory
What MistralAI-User does
MistralAI-User handles user actions in Vibe, the Mistral AI product named in the documentation. When someone asks Vibe a question, the agent may visit a web page to help answer it and include a link to the source in the response.
What Mistral AI states:
- The
MistralAI-Usertoken governs which sites these user requests can be made to. - The agent is not used to crawl the web automatically, nor to collect content for generative AI training.
- The full user-agent string is published, along with a JSON file of IP ranges.
Mistral AI documents two other crawlers: MistralAI-Index, which indexes the web for Mistral search and whose content is not used for training, and MistralAI-Training, which builds training datasets and can be disallowed in robots.txt. Blocking MistralAI-User therefore affects neither indexing nor training.
Mistral does not say outright that this agent always honors robots.txt, nor that it may ignore it. Perplexity uses almost the same wording for Perplexity-User while adding that it generally ignores robots.txt, so the wording alone is not conclusive. That is why this entry keeps a cautious value.
Block or allow MistralAI-User
If the rule is honored, Vibe can no longer read or cite your pages when answering users. Indexing by MistralAI-Index and collection by MistralAI-Training are configured separately.
To block it, add this to your robots.txt:
User-agent: MistralAI-User
Disallow: /To allow it explicitly (copy any private rules you have):
User-agent: MistralAI-User
Allow: /A group naming MistralAI-User replaces the User-agent: * group for it. Build a complete robots.txt with the generator and check it with the tester.
Verify a MistralAI-User visit
Anyone can write “MistralAI-User” in a User-Agent. Paste the IP address and User-Agent from your logs into the IP verifier to know whether the visit is genuine.