[invisit](https://invisit.dev) · [Docs](https://invisit.dev/docs) · [llms.txt](https://invisit.dev/llms.txt) · [llms-full.txt](https://invisit.dev/llms-full.txt)

# Claude-User

> Claude-User is an AI assistant fetcher run by Anthropic. It fetches pages when a Claude user asks a question that needs content from the web.

- Operator: Anthropic
- Kind: AI assistant fetcher
- robots.txt token: Claude-User
- Follows robots.txt: yes
- Source: https://support.claude.com/en/articles/8896518 (checked 2026-11-05)
- Page: https://invisit.dev/bots/claude-user

## What is Claude-User?

It fetches pages when a Claude user asks a question that needs content from the web.

Fetches a page because a person asked an assistant about it, right now. Operators often say robots.txt does not apply to these user-triggered fetches.

Anthropic says blocking Claude-User stops Claude retrieving your pages for user queries, which may reduce your visibility in user-directed search. It warns that blocking its IP addresses instead of using robots.txt may not give a reliable opt-out.

- [Anthropic’s documentation](https://support.claude.com/en/articles/8896518)

## Should you block Claude-User?

Usually allow it. Each fetch is a person asking about your page right now, which is close to a visit. Blocking it in robots.txt may not stop it, since operators often treat these fetches as the person’s own.

## How to block Claude-User in robots.txt

Add a group for its token to robots.txt at the root of your site.

A bot follows only the group that names it, so it ignores your `User-agent: *` rules once it has a group of its own. Repeat any paths you also want kept from it there.

```
User-agent: Claude-User
Disallow: /
```

- [Build a robots.txt for AI bots](https://invisit.dev/tools/robots-txt-generator)

## How to verify a request is really Claude-User

Anyone can send any user agent, so the string alone proves nothing.

Anthropic publishes the IP ranges Claude-User crawls from. A request that claims to be Claude-User from any other address is not Claude-User.

- [Claude-User IP ranges](https://claude.com/crawling/bots.json)

## See when Claude-User reads your site

Bots don’t run JavaScript analytics, so a script tag never sees them. invisit records crawler reads on the server instead, through its server SDK or a Cloudflare Worker, and shows which bots read which pages, next to your visitors.

- [Track crawlers with invisit](https://invisit.dev/docs/server/sdk#crawler-reads)

## Common questions

### What is Claude-User?

Claude-User is an AI assistant fetcher run by Anthropic. It fetches pages when a Claude user asks a question that needs content from the web.

### Is Claude-User safe to block?

Usually allow it. Each fetch is a person asking about your page right now, which is close to a visit. Blocking it in robots.txt may not stop it, since operators often treat these fetches as the person’s own.

### How do I block Claude-User?

Add “User-agent: Claude-User” followed by “Disallow: /” to your robots.txt.