scrapling-fetch-mcp 0.1.2

Simple URL fetcher MCP server for Scrapling. Retrieves HTML/markdown from automation-blocking sites with three protection levels.

Scrapling Fetch MCP Server

A simple Model Context Protocol (MCP) server implementation that integrates with Scrapling for retrieving web content with advanced bot detection avoidance.

Note: This project was developed in collaboration with Claude Sonnet 3.7, using LLM Context to share code during development. Initial vibe code session with Sonnet to get to a working prototype + several curation sessions where I (@restlessronin) refactored and refined with Sonnet's feedback.

Intended Use

This tool is optimized for low volume retrieval of documentation and reference materials (text/html only) from websites that implement bot detection. It has not been designed or tested for general-purpose site scraping or data harvesting.

Features

• Retrieve content from websites that implement advanced bot protection
• Three protection levels (basic, stealth, max-stealth)
• Two output formats (HTML, markdown)

Installation

Install scrapling

uv tool install scrapling
scrapling install

uv tool install scrapling-fetch-mcp

Usage with Claude

Add this configuration to your Claude client's MCP server configuration:

{
  "mcpServers": {
    "Cyber-Chitta": {
      "command": "uvx",
      "args": ["scrapling-fetch-mcp", ">", "/dev/null", "2>&1"]
    }
  }
}

Available Tools

scrapling-fetch

Fetch a URL with configurable bot-detection avoidance levels.

{
  "name": "scrapling-fetch",
  "arguments": {
    "url": "https://example.com",
    "mode": "stealth",
    "format": "markdown",
    "max_length": 5000,
    "start_index": 0
  }
}

Parameters

• url (required): The URL to fetch
• mode (optional, default: "basic"): Protection level
  • basic: Fast retrieval with minimal protection
  • stealth: Balanced protection against bot detection
  • max-stealth: Maximum protection with all anti-detection features
• format (optional, default: "markdown"): Output format (options: html, markdown)
• max_length (optional, default: 5000): Maximum number of characters to return
• start_index (optional, default: 0): Character index to start from in the response (useful for paginated content)

License

Apache 2