Name: Browser Use for AI Agents
Author: KnotFalse

History

11 snapshots

Tracking since Apr 5, 2026.

View as table

Date	Users	Rating	Reviews	Version
Apr 5, 2026	10	—	—	0.2.3
Apr 18, 2026	17	—	—	0.2.3
Apr 23, 2026	43	—	—	0.4.2
Apr 30, 2026	47	—	—	0.4.2
May 7, 2026	60	—	—	0.4.2
May 12, 2026	62	—	—	0.4.2
May 17, 2026	68	—	—	0.4.2
May 24, 2026	82	—	—	0.4.2
May 30, 2026	99	—	—	0.4.2
Jun 6, 2026	96	—	—	0.4.2
Jun 15, 2026	111	—	—	0.4.2
Now	120	—	—	0.4.2

Changelog

Apr 18, 2026

description

Unlock true local-first browser automation for your AI agents.

The Local Multiplexed Browser MCP is a powerful Chrome extension designed to connect your local browser directly to AI code assistants and autonomous agents (such as Cursor, Claude Desktop, or custom CLI tools) using the Model Context Protocol (MCP).

If you are building or using AI web agents, you know the primary bottleneck: the Chrome DevTools Protocol (chrome.debugger) strictly limits attachments to one connection per tab. If multiple agents attempt to control your browser simultaneously, they collide, fail silently, or crash. Furthermore, existing solutions often force your local web traffic through proprietary, subscription-based cloud relays.

This extension, paired with the accompanying Local MCP Bun Server, solves both problems. It acts as a high-performance, multiplexed reverse proxy, allowing multiple concurrent AI agents to share a single Chrome instance safely, entirely on your localhost.

🚀 Why Install This Extension?

Zero Cloud Dependencies (Local-First): Your browser automation stays on your machine. The extension communicates via WebSockets directly to your local loopback (127.0.0.1), ensuring high-speed execution and absolute data privacy. No external servers, no OAuth brokers, no API usage limits.

True Agent Multiplexing: Run Cursor, Claude, Codex, Gemini, OpenCode, and any other custom terminal agents at the same time. The server assigns unique Agent Session IDs (ASID) to dynamically route commands without cross-session contamination. **Other extensions make you pay for this feature.**

Strict Tab Locking Orchestration: Never experience a "Debugger already attached" race condition again. The extension enforces deterministic lock ownership per tab. If Agent A locks Tab 1, Agent B is actively blocked and receives a structured lock conflict error, allowing it to queue or wait.

Rich Diagnostic UI: A neo-industrial popup interface gives you real-time telemetry. View active connections, inspect which agent owns which tab lock, copy your bridge URL, and forcibly terminate runaway agent sessions directly from the browser.

Resilient Crash Recovery: Built for the realities of AI development. If an agent crashes while holding a tab lock, or if the extension restarts, the system auto-reconciles stale state, clears ghost locks, and reconnects without requiring manual cleanup.

🛠️ Exposed MCP Capabilities

When connected to the Local MCP Server, this extension exposes a massive surface area of browser automation tools directly to your LLM:

Tab Management: list_available_tabs, attach_to_tab, detach_from_tab (lock-aware orchestration).

Navigation & State: browser_navigate (URL, back, forward, reload), browser_tabs (new, close, attach).

DOM Intelligence: browser_snapshot (structured DOM tree extraction), browser_extract_content (targeted text extraction), browser_lookup.

Execution & Interaction: browser_evaluate (execute raw JS via Runtime.evaluate), browser_interact (click, type, hover, scroll), browser_fill_form, browser_drag.

Network & Diagnostics: browser_network_requests (capture and filter XHR/Fetch via event listeners), browser_console_messages, browser_performance_metrics.

Media: browser_take_screenshot, browser_pdf_save (export pages to base64 PDF).

Environment Control: browser_window (resize, maximize), browser_handle_dialog, browser_list_extensions, browser_verify_text_visible.

🎯 Who is this for?

Software Engineers using IDEs like Cursor who want their AI to test web applications, reproduce bugs, or read local documentation.

AI Operators building autonomous web-scraping or research agents using frameworks like LangChain, AutoGen, or raw MCP clients.

QA Automation Engineers who want to leverage LLMs to write and execute browser interactions dynamically without writing fragile XPath selectors.

⚠️ Important Setup Requirements

This extension does not operate on its own. It is the browser-side bridge for the Local MCP Bun Server.

To use this extension, you must run the local server on your machine:

Download the server binary from the project repository.

Run the server locally (defaults to ws://127.0.0.1:37777/extension).

Configure your MCP client (e.g., claude_desktop_config.json or Cursor's MCP settings) to point to the local server.

The extension will automatically connect, pulse to indicate readiness, and begin routing agent commands.

(Modified by [KnotFalse] - Originally inspired by the blueprint-mcp architecture, completely rebuilt in Bun/TypeScript for local-first, high-performance multiplexing).