Scrapling Fetch MCP

Source

Helps AI assistants access text content from bot-protected websites. MCP server that fetches HTML/markdown from sites with anti-automation measures using Scrapling.

Catalog onlyCatalog onlySTDIO

Overview

Scrapling Fetch MCP is a tool designed to help large language models (LLMs) access content from bot-protected websites by fetching HTML or markdown content from such sites using Scrapling.

To use Scrapling Fetch MCP, install it via the uv package manager, configure it in your LLM's MCP server settings, and then use it to fetch content from URLs with specified protection levels.

Retrieves content from websites with advanced bot protection. - Offers three protection levels: basic, stealth, and max-stealth. - Supports two output formats: HTML and markdown. - Pagination support for large documents.

Accessing documentation from websites that implement bot detection.
Retrieving reference materials for AI assistants.
Fetching content for summarization tasks in LLMs.

Add to your AI client

Use these steps to connect Scrapling Fetch MCP in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "scrapling-fetch-mcp-cyberchitta": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-scrapling-fetch-mcp-cyberchitta"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "scrapling-fetch-mcp-cyberchitta": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-scrapling-fetch-mcp-cyberchitta"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "scrapling-fetch-mcp-cyberchitta": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-scrapling-fetch-mcp-cyberchitta"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "scrapling-fetch-mcp-cyberchitta": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-scrapling-fetch-mcp-cyberchitta"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "scrapling-fetch-mcp-cyberchitta": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-scrapling-fetch-mcp-cyberchitta"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "scrapling-fetch-mcp-cyberchitta": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-scrapling-fetch-mcp-cyberchitta"
      ]
    }
  }
}

FAQ

Can Scrapling Fetch MCP scrape any website?

No, it is optimized for low volume retrieval from sites with bot protection and is not designed for high-volume scraping or data harvesting.

What are the protection levels?

The tool offers basic, stealth, and max-stealth modes to balance speed and success rate against bot detection.

Is there a limit on the amount of content that can be fetched?

Yes, the maximum length of content that can be retrieved is configurable, with a default of 5000 characters.

Developer tools