MCP

Capture Web Screenshots and Console Logs

BrowserLoop MCP server captures screenshots and console logs from web pages using Playwright for AI development.

Works with playwrightdocker

90
Spark score
out of 100
Updated 4 months ago
Version 1.0.0
Models

Add to Favorites

Why it matters

Automate web browser interactions to capture high-quality screenshots and collect console logs for testing and debugging purposes.

Outcomes

What it gets done

01

Capture full page or element-specific screenshots with customizable formats and quality.

02

Monitor and collect console logs from web pages.

03

Support cookie-based authentication for protected pages.

04

Integrate with CI/CD pipelines using Docker or NPX.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-browserloop | bash

Capabilities

Tools your agent gets

capture_screenshot

Capture a screenshot of a web page with customizable format, quality, and viewport size.

read_console_logs

Read and collect console logs from a web page during or after page load.

capture_element_screenshot

Capture a screenshot of a specific element on a web page.

capture_full_page_screenshot

Capture a full page screenshot including content below the fold.

Overview

BrowserLoop MCP Server

What it does

BrowserLoop MCP Server

How it connects

Archived

Source README

MCP server for capturing screenshots and reading console logs from web pages using Playwright. Supports high-quality image capture with customizable formats, viewport sizes, cookie-based authentication, and screenshots of both full pages and individual elements.

Installation

NPX (Recommended)

# Install Chromium browser (one-time setup)
npx playwright install chromium

# Verify that BrowserLoop works
npx browserloop@latest --version

Docker

# Download and run with Docker
docker run --rm --network host browserloop

# Or use docker-compose for development
git clone <repository-url>
cd browserloop
docker-compose -f docker/docker-compose.yml up

Development Installation

# Clone the repository
git clone <repository-url>
cd browserloop

# Install dependencies
npm install

# Install Playwright browsers (required for screenshots)
npx playwright install chromium

# Build the project
npm run build

Configuration

NPX Configuration

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

Development Configuration

{
  "mcpServers": {
    "browserloop": {
      "command": "node",
      "args": [
        "/absolute/path/to/browserloop/dist/src/index.js"
      ],
      "description": "Screenshot and console log capture server for web pages using Playwright"
    }
  }
}

Configuration with Environment Variables

{
  "mcpServers": {
    "browserloop": {
      "command": "node",
      "args": ["dist/src/mcp-server.js"],
      "env": {
        "BROWSERLOOP_DEFAULT_COOKIES": "/home/username/.config/browserloop/cookies.json",
        "BROWSERLOOP_DEFAULT_FORMAT": "webp",
        "BROWSERLOOP_DEFAULT_QUALITY": "85"
      }
    }
  }
}

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
  • Support for PNG, JPEG, and WebP formats with customizable quality
  • Secure execution in non-root containers
  • Full integration with MCP protocol for AI development tools
  • Customizable viewport sizes and capture options
  • Full page and individual element screenshots

Environment Variables

Optional

  • BROWSERLOOP_DEFAULT_WIDTH - Default viewport width (200-4000)
  • BROWSERLOOP_DEFAULT_HEIGHT - Default viewport height (200-4000)
  • BROWSERLOOP_DEFAULT_FORMAT - Default image format (webp, png, jpeg)
  • BROWSERLOOP_DEFAULT_QUALITY - Default image quality (0-100)
  • BROWSERLOOP_DEFAULT_TIMEOUT - Default timeout in milliseconds
  • BROWSERLOOP_USER_AGENT - Custom user agent string
  • BROWSERLOOP_DEFAULT_COOKIES - Default cookies as file path or JSON string
  • BROWSERLOOP_CONSOLE_LOG_LEVELS - Comma-separated list of log levels to capture

Usage Examples

Take a screenshot of https://example.com
Take a screenshot of https://example.com with width 1920 and height 1080
Take a screenshot of https://example.com in JPEG format with 95% quality
Take a full page screenshot of https://example.com
Take a screenshot of http://localhost:3000 to verify the UI changes

Notes

⚠️ ARCHIVED: This project is archived and will no longer receive updates. With the release of Chrome DevTools MCP, a dedicated MCP server for browser automation is no longer needed. Nearly all code in this repository was automatically generated. BrowserLoop requires Chromium installation via Playwright before capturing screenshots. Cookie-based authentication is supported for capturing screenshots of password-protected pages during development.

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.