OpenCode Browse Tool Enables AI Agents to Access User Browsers
Article Content
- •OpenCode Browse allows AI agents to use real user browsers seamlessly.
- •The tool supports multiple browsers and integrates with various MCP clients.
- •No reported vulnerabilities or active exploitation related to this tool.
OpenCode has launched a new tool, OpenCode Browse, which allows AI agents to interact with users' real browsers, including their tabs, logins, and extensions. This tool operates as a small native MCP server alongside a Chromium extension, enabling agents to perform tasks such as reading pages, clicking, typing, and capturing screenshots in the background. When user interaction is required, such as for logins or 2FA prompts, the tool hands control back to the user. It supports multiple browsers, including Chrome, Edge, and Brave. The installation process involves running a curl command to set up the browse environment for the agents. The tool is designed for use with various MCP clients, including OpenCode and Claude Code. No specific vulnerabilities or exploitation methods were reported in the articles, and the tool appears to be functioning as intended without any known security flaws at this time.
Ask AI about this cluster
Answers cite the sources they use
Timeline
More articles in this cluster (3)
Common questions
What browsers does OpenCode Browse support?
Is there any known vulnerability with OpenCode Browse?
How do I install OpenCode Browse?
Continue Reading
Lazarus Group Targets 30 South Korean Servers Using PHP Vulnerabilities North Korea-linked Lazarus Group has targeted 30 servers in South Korea as part of a larger cyber operation involving 581 servers across 10 countries. The attacks exploit two critical remote code execution vulnerabilities in PHP (CVE-2026-109618 and CVE-2026-109619), allowing unauthorized server command execution. The…