`MistralAI-User`

Mistral says MistralAI-User is for user actions in Vibe. When a person asks Vibe a question, it may visit a page and include a link to the source. Mistral says this token governs which sites those requests can be made to. It is not an automatic crawl and is not used to crawl content for generative AI training. MistralAI-Index and MistralAI-Training are different tokens.

robots.txt token: MistralAI-User
Operator: Mistral
Kind: user_fetch
robots.txt: governs_sites. The vendor says this robots.txt token governs which sites these requests can be made to.
HTTP user-agent: Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; MistralAI-User/1.0; +https://docs.mistral.ai/robots) Mistral publishes this as the full user-agent string.
IP list: https://mistral.ai/mistralai-user-ips.json The page links this JSON URL. On 2026-10-18 it returned HTTP 200 and JSON with creationTime 2025-02-19T12:00:00.000000. Botcard does not copy the address list.
Source: Mistral crawlers. Retrieved 2026-10-18.

JSON

curl -s https://whosthatbot.com/v1/crawlers/mistralai-user

Check this token

tools/call with name check_robots is the same check at POST /mcp. The pasted file disallows MistralAI-User on /docs and allows *. The call does not fetch a host.

curl -s https://whosthatbot.com/mcp -H 'content-type: application/json' -H 'accept: application/json, text/event-stream' -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"check_robots","arguments":{"robots_txt":"User-agent: MistralAI-User\nDisallow: /\n\nUser-agent: *\nAllow: /\n","path":"/docs","ids":["mistralai-user"]}}}'

That call returns fetched_target false. This row is disallow via group MistralAI-User, rule Disallow: /.