BrowserLoop

Created 5 months ago

A Model Context Protocol (MCP) server for taking screenshots and reading console logs from web pages using Playwright.

development documentation public MCP screenshots console logs

What is BrowserLoop?

An MCP server for taking screenshots of web pages using Playwright. Supports high-quality capture with configurable formats, viewport sizes, cookie-based authentication, and both full page and element-specific screenshots.

Documentation

Features

📸 High-quality screenshot capture using Playwright
📝 Console log monitoring and collection from web pages
🌐 Support for localhost and remote URLs
🍪 Cookie-based authentication for protected pages
🐳 Docker containerization for consistent environments
⚡ PNG, JPEG, and WebP format support with configurable quality
🛡️ Secure non-root container execution
🤖 Full MCP protocol integration with AI development tools
🔧 Configurable viewport sizes and capture options
📱 Full page and element-specific screenshot capture
⚠️ Browser warning and error capture

Quick Start# 📦 NPX Usage (Recommended)

npx playwright install chromium\n\n# Test that BrowserLoop works
npx browserloop@latest --version

MCP Configuration

Add BrowserLoop to your MCP configuration file (e.g. ~/.cursor/mcp.json):

{
  "mcpServers": {
    "browserloop": {
      "command": "npx",
      "args": ["-y", "browserloop@latest"],
      "description": "Screenshot and console log capture server for web pages using Playwright"
    }
  }
}

Documentation Links

Server Config

{
  "mcpServers": {
    "browserloop-server": {
      "command": "npx",
      "args": [
        "browserloop"
      ]
    }
  }
}

Links & Status

Repository: github.com

Hosted: No

Global: Yes

Official: Yes

Project Info

Hosted Featured

Created At: Jul 02, 2025

Updated At: Aug 07, 2025

Author: Mattias W.

Category: community

License: GNU Affero General Public License v3.0 or later (AGPL-3.0-or-later)

Tags:

development documentation public