Scrapling Fetch MCP Server

What does “Scrapling Fetch” MCP Server do?

The Scrapling Fetch MCP Server is a specialized Model Context Protocol (MCP) server designed to help AI assistants access text content from websites that implement bot protection and anti-automation measures. By leveraging the underlying Scrapling tool, it bridges the gap between what users can see in their browsers and what AI agents can retrieve, making it possible to fetch HTML or markdown from sites that would otherwise block automated scrapers. Scrapling Fetch MCP is optimized for low-volume retrieval of documentation and reference materials, specifically focusing on text and HTML rather than general-purpose site scraping. This makes it a valuable asset for development workflows that require access to protected online documentation or context enrichment, while respecting site boundaries and intended use.

List of Prompts

No explicit prompt templates are documented in the repository.

List of Resources

No explicit MCP resources are documented in the repository.

List of Tools

• s-fetch-page: Retrieves complete web pages, supporting pagination to allow incremental fetching of large documents.
• s-fetch-pattern: Extracts specific content from web pages by matching user-supplied regex patterns, along with configurable surrounding context.

Use Cases of this MCP Server

• Accessing Bot-Protected Documentation: Developers can retrieve documentation or reference material from sites that would otherwise block automated tools, enabling AI assistants to answer questions using up-to-date, protected sources.
• Extracting Specific Information: Use regular expressions to extract targeted data (such as API keys, configuration snippets, or references) from large documentation pages, reducing noise and focusing on relevant context.
• Summarizing Web Content: Fetch entire web pages and summarize their content, making it easier for users to digest large or complex documentation.
• Contextual Assistance in IDEs: Integrate the server with development environments, allowing AI tools to fetch and provide context-aware assistance using protected online resources.
• Incremental Page Retrieval: Handle large documents by paginating requests, ensuring that even extensive references can be processed without exhausting resources.

How to set it up

Windsurf

No specific instructions for Windsurf are documented in the repository.

Claude

1. Ensure prerequisites: Python 3.10+ and uv package manager are installed.
2. Install dependencies:

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

3. Locate your Claude client’s configuration file.
4. Add the Scrapling Fetch MCP server:

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

5. Save and restart Claude client to apply configuration.

Securing API Keys

No explicit documentation on API key usage or environment variable configuration is provided.

Cursor

No specific instructions for Cursor are documented in the repository.

Cline

No specific instructions for Cline are documented in the repository.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "scrapling-fetch": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “scrapling-fetch” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

| Roots Support | ⛔ | Not mentioned |

Between the two tables, the Scrapling Fetch MCP Server stands out by providing clear and useful tooling for protected web retrieval, but lacks standardized prompts, resource declaration, and advanced security/environment variable documentation. Based on its features and documentation, we would rate this MCP a 6/10 for overall completeness and utility.

MCP Score