Claude Code now has a built-in browser that lets the AI read, click, and type on external websites
Quick Answer
Anthropic has integrated a browser into Claude Code, enabling it to read, click, and type on external websites directly within the app.
Quick Take
Anthropic has integrated a browser into Claude Code, enabling it to read, click, and type on external websites directly within the app. This feature includes safety checks to prevent unauthorized actions, and organizations can restrict access through an allowlist. Users requiring logged-in sessions should use the Chrome extension instead.
Key Points
- Claude Code can now interact with external websites directly within the app.
- Safety checks prevent unauthorized actions like purchases or account creation.
- Organizations can restrict browser access via an allowlist or disable it entirely.
- Users wanting to log in should utilize the Chrome extension instead.
📖 Reader Mode
~1 min readAnthropic added an integrated browser window to Claude Code. Claude can now open, read, click, and type on web pages directly inside the app. That includes documentation sites, issue trackers, and similar resources. The browser works like a tab-based browser and opens with a keyboard shortcut. Claude uses the same tools it already uses to preview local apps, but with extra safety checks. Classifiers screen any write actions on external sites, and Claude won't buy anything, create accounts, or bypass CAPTCHAs without user consent. The browser runs on a clean profile with no saved logins.
Organizations can restrict access to external sites through an allowlist or disable the browser tools entirely, as Anthropic announced on X. Anyone who wants Claude to act within their own logged-in sessions should use the Chrome extension instead.
— Originally published at the-decoder.com
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from The Decoder
See more →
An AI model programmed nonstop for 19 days on a single MirrorCode task that cost $2,600 to run
Epoch AI's MirrorCode benchmark reveals Claude Opus 4.7 as the leader with a 56% solve rate, reconstructing a 16,000-line toolkit in 14 hours. Despite this, all models tested struggle with the most complex tasks, highlighting limitations in current AI capabilities. The single task consumed $2,600 over 19 days, raising questions about cost-effectiveness in AI development.
