MistralAI-Index
The index Mistral's assistant answers from
What MistralAI-Index does
MistralAI-Index is the crawler behind what Mistral's assistant can retrieve. Blocking it is the decision about whether Mistral can find you at all.
Two IP prefixes, the smallest list of any crawler in this directory, which says something about the scale of the operation relative to OpenAI's or Google's. It also makes verification trivial.
Mistral follows the same three-way pattern as OpenAI, Anthropic, Perplexity and Amazon, publishing an index crawler and a user fetcher as separate tokens with separate IP lists.
MistralAI-Index is not MistralAI-User
MistralAI-Index builds what Mistral can retrieve. MistralAI-User fetches a page because a person asked for it.
What MistralAI-User does insteadHow to block MistralAI-Index
Add this to the robots.txt at the root of your domain, alongside what is already there rather than replacing it.
robots.txt
User-agent: MistralAI-Index
Disallow: /What that costs you: Mistral has nothing of yours to retrieve.
To allow it instead, write nothing. A crawler with no group of its own follows your User-agent: * rules, and giving it a named group with Allow: / detaches it from those rules entirely — including any path you disallow there.
Find it in your logs
Mistral names the token but does not publish a full user-agent string for it, so match on the token itself.
To find every visit it has made, and the addresses it came from:
Terminal
grep -F 'MistralAI-Index' /var/log/nginx/access.log | awk '{print $1}' | sort | uniq -c | sort -rnCheck that it is really MistralAI-Index
A user agent is a string the visitor chooses, so on its own it proves nothing — anyone can send yours. Mistral publishes the addresses MistralAI-Index fetches from: 2 prefixes when we read the file, last changed on 19 April 2026. Take an address out of your logs and check it against that list.
Terminal
curl -s https://mistral.ai/mistralai-index-ips.json | python3 -c "
import sys, json, ipaddress
addr = ipaddress.ip_address('203.0.113.10') # the address from your logs
nets = json.load(sys.stdin)['prefixes']
print(any(addr in ipaddress.ip_network(n.get('ipv4Prefix') or n['ipv6Prefix']) for n in nets))
"False means something else is wearing the name, and it is under no obligation to respect anything in your robots.txt. That is the traffic worth blocking at the edge, rather than the crawler that was asking politely.
Should you block MistralAI-Index?
The same shape as every retrieval decision here. Blocking it removes you from Mistral's answers and buys nothing elsewhere.
Mistral's reach is smaller than the vendors at the top of this directory, so the stakes are lower — but the decision is identical, and a blanket snippet that catches it usually catches the ones that matter too.
Questions
- Is MistralAI-Index used for training?
- Mistral documents it as the indexing crawler and publishes MistralAI-User separately for user actions. Read their robots documentation for the current position rather than assuming the split matches another vendor's.
The user agent and IP figures on this page were read from Mistral’s own URLs on 14 September 2026. Blocking figures come from our survey of 170 well-known sites across 10 categories on 14 September 2026, 148 of which returned a readable robots.txt.
Is MistralAI-Index allowed on your site right now?
The checker reads your live robots.txt and reports every token in this directory, with the exact directive that decided each one.