Back to browse
GitHub Repository

AI-controlled browser farm on your machine. 36 MCP tools for Claude Code & Cursor — run N Chromium instances with device emulation, screenshots, network/geolocation simulation. Cross-platform: Windows GUI, headed & headless on Linux/macOS.

10 starsC#

GDD–36 MCP tools to run N isolated Chromium browsers from Claude/Cursor

by imVSall·May 17, 2026·1 point·0 comments

AI Analysis

●●●BangerSolve My ProblemShip It

Local browser farm for AI agents replaces cloud grids like BrowserStack.

Strengths
  • 36 MCP tools enable granular AI control over browser state.
  • Device emulation profiles cover 22 types without needing physical device labs.
  • Pre-compiled binaries across three platforms mean no Python environment hell.
Weaknesses
  • Running multiple Chromium instances locally consumes significant system RAM quickly.
  • Lacks anti-detect fingerprinting features needed for serious scraping use cases.
Target Audience

AI agent developers, QA engineers

Similar To

BrowserStack · Playwright · browser-use

Similar Projects