Scrapling Fetch MCP

An MCP server that helps AI assistants access text content from websites that implement bot detection, bridging the gap between what you can see in your browser and what the AI can access.

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.

Note: This project was developed in collaboration with Claude Sonnet 3.7, using LLM Context.

Installation

1. Requirements:

   • Python 3.10+
   • uv package manager

2. Install dependencies and the tool:

uv tool install scrapling
scrapling install
uv tool install scrapling-fetch-mcp

Setup with Claude

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

{
  "mcpServers": {
    "Cyber-Chitta": {
      "command": "uvx",
      "args": ["scrapling-fetch-mcp"]
    }
  }
}

Available Tools

This package provides two distinct tools:

1. s-fetch-page: Retrieves complete web pages with pagination support
2. s-fetch-pattern: Extracts content matching regex patterns with surrounding context

Example Usage

Fetching a Complete Page

Human: Please fetch and summarize the documentation at https://example.com/docs

Claude: I'll help you with that. Let me fetch the documentation.

https://example.com/docs
basic

Based on the documentation I retrieved, here's a summary...

Extracting Specific Content with Pattern Matching

Human: Please find all mentions of "API keys" on the documentation page.

Claude: I'll search for that specific information.

https://example.com/docs
basic
API\s+keys?
150

I found several mentions of API keys in the documentation:
...

Functionality Options

• Protection Levels:

  • basic: Fast retrieval (1-2 seconds) but lower success with heavily protected sites
  • stealth: Balanced protection (3-8 seconds) that works with most sites
  • max-stealth: Maximum protection (10+ seconds) for heavily protected sites

• Content Targeting Options:

  • s-fetch-page: Retrieve entire pages with pagination support (using start_index and max_length)
  • s-fetch-pattern: Extract specific content using regular expressions (with search_pattern and context_chars)
    • Results include position information for follow-up queries with s-fetch-page

Tips for Best Results

• Start with basic mode and only escalate to higher protection levels if needed
• For large documents, use the pagination parameters with s-fetch-page
• Use s-fetch-pattern when looking for specific information on large pages
• The AI will automatically adjust its approach based on the site's protection level

Limitations

• Designed only for text content: Specifically for documentation, articles, and reference materials
• Not designed for high-volume scraping or data harvesting
• May not work with sites requiring authentication
• Performance varies by site complexity

License

Apache 2

Shared threads will appear here, showcasing real-world applications and insights from the community. Check back soon for updates!