mistralai-user
Mistral crawler, type: ai assistant.
- 57,922sites name it in robots.txt
- 31,143block it fully (53.8%)
- 15,988block some paths
- 10,791allow it explicitly
About this crawler
MistralAI-User is used when users ask the Mistral assistant a question; it may visit a web page to help answer and include a link to the source. It is not used for crawling the web in any automatic fashion, nor to crawl content for generative AI training.
- User-Agent
Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; MistralAI-User/1.0; +https://docs.mistral.ai/robots)- robots.txt token
mistralai-user- Respects robots.txt
- yes (third party: source)
- Published IP ranges
- https://mistral.ai/mistralai-user-ips.json
- Operator page
- https://docs.mistral.ai/robots
- Page documents three separate agents: MistralAI-User, MistralAI-Index and MistralAI-Training, each with its own UA and (for User and Index) IP JSON list (mistralai-index-ips.json).
- Fetched page text names the product 'Vibe'; a search snippet of the same page said 'Le Chat', so the page wording may have changed.
- Fetched summary only clearly stated that webmasters can disallow the training agent in robots.txt; a robots.txt statement for MistralAI-User was not confirmed from the fetch.
Including sites that block it only through the * group, 4.21% of all sites with a robots.txt keep it out.