This repository provides an MCP server, `scrapling-fetch-mcp`, enabling AI assistants to access text content from websites employing bot detection. It offers tools for fetching complete pages and extracting content based on patterns.
This tool is an MCP server designed to enable AI assistants to access text content from websites with bot detection. It bridges the gap between browser accessibility and AI access.
Intended Use: Optimized for low-volume retrieval of documentation and reference materials (text/HTML only). Not designed for general-purpose scraping.
Installation: Requires Python 3.10+ and the uv package manager. Install dependencies and the tool using uv tool install scrapling, scrapling install, and uv tool install scrapling-fetch-mcp.
Setup with Claude: Configure your Claude client with the provided JSON snippet to integrate the MCP server.
Available Tools:
s-fetch-page: Retrieves complete web pages with pagination support.s-fetch-pattern: Extracts content matching regex patterns with surrounding context.Functionality Options: Protection levels (basic, stealth, max-stealth) and content targeting options for page retrieval or pattern extraction.
Limitations: Designed for text content only, not for high-volume scraping, and may not work with sites requiring authentication.
License: Apache 2
cyberchitta/scrapling-fetch-mcp
March 13, 2025
March 27, 2025
Python