OpenCode Browse has launched an MCP server and a Chromium extension designed to allow AI agents to utilize a user's actual web browser environment. This integration means agents can access existing tabs, use pre-configured logins, and leverage installed browser extensions, eliminating the need for separate setups or key management.
The system operates by opening agent-controlled tabs in the background, grouped and collapsed to minimize user disruption. For tasks requiring direct user input, such as logins, two-factor authentication (2FA) prompts, or payments, the system hands control of the tab back to the user. Once the user completes the action, the agent can resume its operation.
OpenCode Browse supports various Chromium-based browsers, including Chrome, Edge, Brave, Arc, Helium, Vivaldi, and Opera. Additional features include the ability to lend an agent an open tab, record and capture screenshots, tab recordings, and network traffic. Agents can also be restricted to specific sites defined by the user.
Installation primarily involves installing the Chrome extension, which guides the user through the remaining setup steps. Direct CLI installation options are also available for npm and bun. The system is compatible with various MCP clients, including OpenCode, Claude Code, Cursor, Codex, and Zed.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's briefNew every morning, and the back catalogue is archived by date.
OpenCode Browse released an MCP server and Chromium extension that allows AI agents to interact with a user's web browser, including existing tabs, logins, and extensions. The system operates by opening agent tabs in the background and providing handoff capabilities for user intervention on tasks like logins or 2FA prompts.