Skip to content

See where you stand

Change it

Works withWordPressShopifyWebflowGitHubGoogleSlackAll integrations
FixesFixes now ship to WordPress, Shopify, Webflow and GitHub

By team

By goal

Done for you

Not sure where to start? Take a guided tour.Book a demo
Customer storyHow the voice AI company Futuro grew its traffic3×AI traffic in 60 days

Learn

Data and research

FreeAI Site GraderAI Query Scannerllms.txt GeneratorAll free tools
Open dataWhere AI sends people, across more than 6,000 sites

Mistral AILive fetcher

MistralAI-User

MistralAI-User is a Mistral user-action fetcher for Vibe responses that need a source page.

Reads a page when someone asks Le Chat about it.

Get the robots.txt ruleMistral AI documentation
Is MistralAI-User allowed on your site?3 Mistral AI bots

Reads your live robots.txt and applies the same rules these crawlers use. Nothing is stored.

robots.txt token
MistralAI-User
Follows robots.txt
Yes, documented
How to verify it
Published IP ranges
Last checked
21 July 2026

Should you block MistralAI-User?

Usually not. It reads a page only when a person asks Le Chat about it, so blocking it hides your page from someone already looking for it.

What blocking each Mistral AI bot does
Mistral AI botJobIf you block it
MistralAI-TrainingTrainingBlocking it opts your content out of Mistral training use while leaving MistralAI-Index free to keep you retrievable in Le Chat.
MistralAI-IndexSearchBlocking it can reduce the chance that Mistral search can find and cite your pages.
MistralAI-UserThis pageUser fetchA hit usually maps to a user asking Mistral to read or cite a specific URL.
robots.txt
User-agent: MistralAI-User
Disallow: /

Asks MistralAI-User not to crawl any page. Other Mistral AI bots are unaffected. Add it to the robots.txt file at the root of your site, above any wider rules.

Ignored robots.txt?

Whether to allow MistralAI-User is a policy call. Either way, check which AI platforms actually send you human visitors before assuming crawl volume equals value.

Spot it in your logs.

Match the name, then check where the request came from. Anyone can copy a user-agent.

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

Version numbers change. Match the highlighted name, not the whole string.

  1. 1

    Match the name

    Search your server or CDN log for MistralAI-User, case-insensitive. A match is a clue, not proof.

  2. 2

    Check the published IP ranges

    Compare the request’s source with the list Mistral AI publishes. Anything outside it is not Mistral AI. mistral.ai/mistralai-user-ips.json

Is this really MistralAI-User?

Published addresses

Paste an address that claims to be MistralAI-User. It is checked against Mistral AI’s published list. Nothing is stored.

Check any crawler’s address

Serve the content in HTML

The cited operator material does not verify JavaScript rendering. Serve useful HTML before client-side JavaScript where possible.

How active is MistralAI-User?

Measured across the sites connected to Trakkr, 27 July 2026 to 25 October 2026.

27%

of connected sites saw MistralAI-User in the four weeks to 25 October 2026. That is 28 of 104.

100%75%50%25%5%
MistralAI-User visited between 3% and 27% of connected sites each week from 27 July 2026 to 25 October 2026.

Share of connected sites it visited each week

Rank by reach
18 of 26
Typical site, per week
33 requests
Sites reached, 13 weeks
30 of 135

Most widespread AI crawlers

Share of connected sites each one visited, last four weeks.

  1. 1OAI-SearchBot84%
  2. 2ClaudeBot84%
  3. 3GPTBot67%
  4. 4Amazonbot61%
  5. 5ChatGPT-User56%
  6. 6PerplexityBot56%
  7. 7Applebot51%
  8. 18MistralAI-User27%
All 26 measured crawlers
How this is measured

Finalized daily crawler summaries from sites connected to Trakkr, grouped by the crawler named in each request. Trakkr’s own site is excluded. A site counts as reached in a week when it logged at least one request from MistralAI-User. The typical figure is the median weekly requests among the sites it reached.

  • This is a sample of connected sites, not the whole web.
  • A matching user-agent does not prove the named operator sent the request.
  • Requests are not unique pages, training use or citations.
  • Crawlers seen on fewer than 10 sites are not shown. Classic search crawlers such as Googlebot are not collected on every site, so they are left out.

Questions, answered.

MistralAI-User is a Mistral user-action fetcher for Vibe responses that need a source page.

Sources.

Officially documented. Operator facts and Trakkr’s measurements keep separate dates.

  1. [1]
    Mistral AI crawler documentation

    Officially documented · checked 21 July 2026

    docs.mistral.ai/robots

First verified 21 July 2026. Last source check 21 July 2026. Activity measured to 25 October 2026.

All AI crawlers

See which AI crawlers read your site.

Trakkr shows which bots, MistralAI-User included, visit which pages each day, and whether the answers they feed mention you.

14-day free trial. Cancel anytime.