Description

The Scrapling MCP server brings advanced web scraping capabilities to AI assistants, featuring six specialized tools for different scraping scenarios: basic HTTP requests with browser fingerprint impersonation, dynamic content fetching with Chromium/Chrome, and stealth scraping using a modified Camoufox browser to bypass Cloudflare Turnstile and other anti-bot protections. Built by the Scrapling team, it differentiates itself from other scraping tools by allowing CSS selector-based content filtering before passing data to the AI, significantly reducing token consumption and improving efficiency compared to solutions that extract entire pages first. The implementation supports bulk operations for parallel processing, proxy integration, and multiple output formats (Markdown, HTML, clean text), making it ideal for e-commerce data collection, content monitoring, and automated research workflows where anti-bot bypass and targeted extraction are essential.

Installation

npx -y scrapling

npm install scrapling

git clone https://github.com/d4vinci/scrapling

Claude Desktop Configuration

Add this configuration to your Claude Desktop config file to enable this MCP server:

Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json

Config file location: %APPDATA%\Claude\claude_desktop_config.json

Config file location: ~/.config/Claude/claude_desktop_config.json

claude_desktop_config.json

{
  "mcpServers": {
    "scrapling": {
      "command": "npx",
      "args": [
        "-y",
        "scrapling"
      ]
    }
  }
}