---
title: "Claude computer use: user agent and token | Agent Ready Crawlers"
description: "Claude computer use from Anthropic: no robots.txt token, task agent purpose and what a site can check; no exact user-agent string is published."
canonical: https://agentreadycrawlers.com/crawlers/claude-computer-use
site: "Agent Ready Crawlers"
last_updated: 2026-11-04
section: "Crawlers"
---

# Claude computer use: user agent and token | Agent Ready Crawlers

> Claude computer use from Anthropic: no robots.txt token, task agent purpose and what a site can check; no exact user-agent string is published.

Source: https://agentreadycrawlers.com/crawlers/claude-computer-use
Site: Agent Ready Crawlers
Last reviewed: 2026-11-04

Browsing agent from Anthropic

# Claude computer use (API tool)

In short

Claude computer use (API tool) is Anthropic's browsing agent. Claude computer use has no robots.txt token, so robots.txt cannot address it and the crawl cannot measure a block rate. The operator publishes nothing a site can check. Claude computer use has no operator bot documentation, checked 2026-11-04. Hosted browsers it runs inside (Browserbase, AgentCore, Cloudflare Browser Rendering) may sign requests.

Operator

[Anthropic](https://agentreadycrawlers.com/crawlers/operator/anthropic/) Vendor profile: [Anthropic](https://agentreadycrawlers.com/vendors/anthropic/)

Purpose

Task agent [All task agent rows](https://agentreadycrawlers.com/crawlers/purpose/task-agent/). A browsing agent that clicks, fills forms and finishes a job for a person.

User-agent string

No exact string is published. What the operator or a third party says: Whatever browser the developer runs; no Anthropic identifier

robots.txt token

None. No robots.txt line can address this agent.

Respects robots.txt

No documentation

operator publishes no bot documentation (checked 2026-11-04). The computer use tool runs in the developer's own environment, so requests come from the developer's infrastructure. [Source](https://docs.anthropic.com/en/docs/agents-and-tools/tool-use/computer-use-tool), read 2026-11-04.

Operator publishes no bot documentation (checked 2026-11-04).

Verification

Nothing published

The operator publishes no list, reverse DNS pattern or key directory a site owner can check. [Documentation](https://docs.anthropic.com/en/docs/agents-and-tools/tool-use/computer-use-tool), read 2026-11-04.

IP ranges

Not published.

Rate behaviour

Set by the developer.

Block rate

None: the agent has no token, so a robots.txt block rate does not exist.

Documentation

Operator publishes no bot documentation (checked 2026-11-04). [Closest page read](https://docs.anthropic.com/en/docs/agents-and-tools/tool-use/computer-use-tool).

Note. Treat as the developer's traffic. Hosted browsers it runs inside (Browserbase, AgentCore, Cloudflare Browser Rendering) may sign requests.

## Allow and refuse lines

This agent has no robots.txt token, so there are no lines to copy. Without a token, a published list or a signature, a site owner cannot tell it from an ordinary visitor by request alone.

Refusing or allowing in robots.txt states a preference. For this row the operator or its documentation says robots.txt may not govern the fetch, so enforcement belongs in your WAF.

## Anthropic in the Verification Ledger

One shared IP list for all three bots; no key directory at claude.ai or claude.com (404, 2026-11-04); nothing for Claude in Chrome. [All operators](https://agentreadycrawlers.com/verification/).

IP lists

-   [claude.com/crawling/bots.json](https://claude.com/crawling/bots.json)

Reverse DNS

publishes nothing

Key directory

publishes nothing

Cloudflare

not confirmed on Radar (directory slug not found, 2026-11-04)

Visa TAP registry

no public operator-level registration found (checked 2026-11-04)

Mastercard Agent Pay

no public operator-level registration found (checked 2026-11-04)

## Other Anthropic rows

-   [ClaudeBot](https://agentreadycrawlers.com/crawlers/claudebot/) Training token ClaudeBot
-   [Claude-User](https://agentreadycrawlers.com/crawlers/claude-user/) Live answer fetch token Claude-User
-   [Claude-SearchBot](https://agentreadycrawlers.com/crawlers/claude-searchbot/) Search index token Claude-SearchBot
-   [anthropic-ai (legacy token)](https://agentreadycrawlers.com/crawlers/anthropic-ai/) Training token anthropic-ai
-   [Claude in Chrome](https://agentreadycrawlers.com/crawlers/claude-in-chrome/) Task agent no token
-   [Claude Duet cloud browser](https://agentreadycrawlers.com/crawlers/claude-duet/) Task agent token Claude-Agent

## Sources

-   [docs.anthropic.com: computer use tool](https://docs.anthropic.com/en/docs/agents-and-tools/tool-use/computer-use-tool) read 2026-11-04
-   [Does Anthropic crawl data from the web, and how can site owners block the crawler?](https://support.claude.com/en/articles/8896518-does-anthropic-crawl-data-from-the-web-and-how-can-site-owners-block-the-crawler) read 2026-11-04

Last reviewed 2026-11-04