VQV Signal

AI AT WORK WATCH TECHNICAL

OpenCode releases Browse, a tool that lets coding agents use a user's real browser profile

According to a post on X by @opencode, OpenCode has released Browse, which combines an MCP server with a Chromium extension. The tool lets agents use the user's actual browser profile, including tabs, logins and extensions, through Playwright in background tab groups. Agents can hand tabs back to the user for logins, 2FA or payments, and sessions can be limited to allowlisted sites. The source says it works with OpenCode, Claude Code, Cursor, Codex, Zed and other MCP clients.

Source: Scobleizer News Pulse (X) · x.com Found via Robert Scoble’s Scobleizer News Pulse · a post on X, not independently verified Published 2026-11-07T05:50:00+00:00 Detected 2026-11-07T14:20:48+00:00
View original source

According to a post on X by @opencode, OpenCode has released Browse, which combines an MCP server with a Chromium extension. The tool lets agents use the user's actual browser profile, including tabs, logins and extensions, through Playwright in background tab groups. Agents can hand tabs back to the user for logins, 2FA or payments, and sessions can be limited to allowlisted sites. The source says it works with OpenCode, Claude Code, Cursor, Codex, Zed and other MCP clients.

AI-assisted summary based on the listed source.

OpenCode ships Browse, an MCP server plus Chromium extension that lets agents use your actual browser profile, tabs, logins and extensions via Playwright in background tab groups. Agents hand tabs back for logins, 2FA or payments, and sessions can be limited to allowlisted sites; it works with OpenCode, Claude...

Developers using coding agents may gain a way to have them work inside their existing logged-in browser sessions instead of a separate clean browser. Limiting sessions to allowlisted sites and handing control back for logins or payments are the safeguards the source describes. Teams should watch how these controls work in practice and how they are documented.

Teams using AI at work may want to compare this against current productivity and review workflows.

Signal Strength 94% Technical label WATCH Public Interest 49 Category AI AT WORK Reader Depth TECHNICAL

Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.

Public Interest components
Recognizable Entity Score 68 Practical Impact Score 28 Novelty Interest Score 70 Consequence Score 30 Curiosity Score 16 Shareability Score 61

VQV surfaced this signal because it is recent, relevant to AI Coding Tools, connected to Scobleizer News Pulse (X).