Scrapling Fetch MCP logo

Scrapling Fetch MCP

by cyberchitta

Scrapling Fetch MCP is an MCP server designed to help AI assistants access text content from websites with bot detection. It bridges the gap between browser accessibility and AI access for documentation and reference materials.

View on GitHub

Last updated: N/A

What is Scrapling Fetch MCP?

Scrapling Fetch MCP is an MCP (Multi-Context Processing) server that enables AI assistants to retrieve text content from websites that employ bot detection mechanisms. It provides tools to fetch entire pages or extract specific content based on patterns.

How to use Scrapling Fetch MCP?

To use Scrapling Fetch MCP, first install the required dependencies (Python 3.10+ and uv). Then, install the scrapling and scrapling-fetch-mcp packages using uv. Configure your Claude client with the provided JSON snippet to integrate the server.

Key features of Scrapling Fetch MCP

  • Retrieves content from bot-protected websites

  • Supports fetching complete web pages with pagination

  • Extracts content using regex patterns with context

  • Offers different protection levels (basic, stealth, max-stealth)

  • Integrates with Claude AI assistant

Use cases of Scrapling Fetch MCP

  • Retrieving documentation for AI summarization

  • Extracting specific information from reference materials

  • Accessing articles behind bot detection

  • Providing AI assistants with up-to-date information from dynamic websites

FAQ from Scrapling Fetch MCP

What is the intended use of Scrapling Fetch MCP?

It is optimized for low-volume retrieval of documentation and reference materials (text/HTML only) from websites that implement bot detection.

What are the available tools in this package?

The package provides two tools: s-fetch-page (retrieves complete web pages with pagination support) and s-fetch-pattern (extracts content matching regex patterns with surrounding context).

What are the different protection levels?

The protection levels are basic (fast retrieval, lower success), stealth (balanced protection), and max-stealth (maximum protection for heavily protected sites).

What content types does Scrapling Fetch MCP support?

It is designed only for text content, specifically for documentation, articles, and reference materials.

Can it be used for high-volume scraping?

No, it is not designed for high-volume scraping or data harvesting.