MCP Url Fetcher

🚀 MCP URL Format Converter

A Model Context Protocol (MCP) server that fetches content from any URL and converts it into the desired output format.

🚀 Quick Start

The MCP URL Format Converter is a powerful tool that enables users to retrieve content from any URL and transform it into various formats, including HTML, JSON, Markdown, or plain text. It's designed to work seamlessly with any MCP-compatible client, such as Claude for desktop, allowing large language models to access, convert, and analyze web content in a consistent format.

✨ Features

• 🔄 Format Conversion: Convert any web content into HTML, JSON, Markdown, or plain text.
• 🌐 Universal Input Support: Handle websites, APIs, raw files, and more.
• 🔍 Intelligent Content Recognition: Automatically detect the source format.
• 🧰 Powerful Library Support:
  • Use Cheerio for HTML parsing.
  • Employ Marked for Markdown processing.
  • Leverage Fast-XML-Parser for XML handling.
  • Utilize CSVtoJSON for CSV conversion.
  • Apply SanitizeHTML for content sanitization.
  • Use Turndown for HTML to Markdown conversion.
• 🔧 Advanced Format Processing:
  • HTML parsing and metadata extraction.
  • JSON pretty-printing and structure preservation.
  • Markdown rendering and style application.
  • CSV to table conversion.
  • XML to JSON conversion.
• 📜 History Tracking: Maintain a log of recently accessed URLs.
• 🛡️ Security Focus: Content sanitization to prevent XSS attacks.

📦 Installation

Prerequisites

• Node.js 16.x or higher
• npm or yarn

Quick Start

1. Clone the repository:

git clone https://github.com/yourusername/mcp-url-converter.git
cd mcp-url-converter

2. Install dependencies:

npm install

3. Start the server:

node index.js

💻 Usage Examples

Basic Usage

The tool allows users to fetch content from any URL and convert it into the desired format. Supported formats include HTML, JSON, Markdown, and plain text.

Advanced Usage

Before installation, ensure your system meets the following requirements:

• Node.js version >=16.x
• npm or yarn installed correctly

Then follow these steps:

1. Clone this repository locally.
2. Run npm install in the project directory to install all dependencies.
3. Start the server to begin using it.

# Example: Convert HTML to JSON
curl -X POST http://localhost:3000/convert \
     --data-raw '{"url":"https://example.com","format":"json"}'

📚 Documentation

🔧 Technical Details

The tool implements several security measures:

• Use SanitizeHTML for content sanitization to prevent XSS attacks.
• Content validation and security checks before processing.
• Error handling and default security settings.
• Input parameter validation (using Zod).
• Security of output encoding.

You can test the tool via the MCP checker:

npm run test

Common Issues

Connection Errors

If you encounter connection errors, check if the URL is correct and accessible.

Conversion Errors

Some complex content may not be successfully converted to the desired format.

Cross-Origin Issues

Some websites may block requests from unknown sources.

Debug Mode

To get more debugging information, set the DEBUG environment variable:

DEBUG=mcp:* npm start

📄 License

This project is released under the MIT License. See the LICENSE file for details.

Acknowledgments

• Built using the Model Context Protocol.
• Utilizes modern, actively maintained, and security-focused libraries.
• Content sanitization is based on OWASP recommendations.

Last Updated: March 29, 2025