Scrapling Fetch MCP Server

Browser AutomationPython

Access text content from websites with bot protection

Available Tools

s-fetch-page

Retrieves complete web pages with pagination support. Parameters include 'url', 'mode' (basic/stealth/max-stealth), 'start_index', and 'max_length'.

s-fetch-pattern

Extracts content matching regex patterns with surrounding context. Parameters include 'url', 'mode' (basic/stealth/max-stealth), 'search_pattern', and 'context_chars'.

Scrapling Fetch bridges the gap between what you can see in your browser and what AI assistants can access. It helps AI assistants retrieve text content from websites that implement bot detection and anti-automation measures, using the Scrapling library. This tool is specifically optimized for low-volume retrieval of documentation, articles, and reference materials from protected websites. It offers multiple protection levels to balance between speed and success rate, allowing AI assistants to access content that would otherwise be blocked.

Overview

Scrapling Fetch enables AI assistants to access text content from websites that implement bot detection and anti-automation measures. This tool is specifically designed for retrieving documentation and reference materials, not for general-purpose scraping or data harvesting.

Installation

To use Scrapling Fetch, you'll need:

Python 3.10 or higher
The uv package manager

Install the required dependencies with these commands:

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

Configuration

To configure your AI assistant to use Scrapling Fetch, add the following to your client's MCP server configuration:

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

Usage Options

Protection Levels

Scrapling Fetch offers three protection levels to balance between speed and success rate:

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

It's recommended to start with basic mode and only escalate to higher protection levels if needed.

Content Targeting

Depending on your needs, you can use different approaches to retrieve content:

Use s-fetch-page to retrieve entire pages with pagination support
Use s-fetch-pattern to extract specific content using regular expressions

For large documents, consider using the pagination parameters with s-fetch-page or use s-fetch-pattern when looking for specific information on large pages.

Limitations

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