nathanonn mcp url fetcher

WHAT IT CONNECTS

nathanonn mcp url fetcher 为 AI Agent 提供什么

• 🔄 **Format Conversion**: Transform any web content to HTML, JSON, Markdown, or plain text
• 🌐 **Universal Input Support**: Handle websites, APIs, raw files, and more
• 🔍 **Automatic Content Detection**: Intelligently identifies source format
• 🧰 **Robust Library Support**: Uses industry-standard libraries:
• Cheerio for HTML parsing
• Marked for Markdown processing
• Fast-XML-Parser for XML handling
• CSVtoJSON for CSV conversion
• SanitizeHTML for security
• Turndown for HTML-to-Markdown conversion
• 🔧 **Advanced Format Processing**:
• HTML parsing with metadata extraction
• JSON pretty-printing and structure preservation
• Markdown rendering with styling
• CSV-to-table conversion
• XML-to-JSON transformation
• 📜 **History Tracking**: Maintains logs of recently fetched URLs
• 🛡️ **Security Focus**: Content sanitization to prevent XSS attacks
• Node.js 16.x or higher
• npm or yarn
• Clone the repository:
• Install dependencies:
• Build the project:
• Run the server:
• Open your Claude for Desktop configuration file:
• macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
• Windows: `%APPDATA%\Claude\claude_desktop_config.json`
• Add the URL converter server to your configuration:
• Restart Claude for Desktop
• `url` (string, required): The URL to fetch content from
• `format` (string, optional): Format to convert to (`auto`, `html`, `json`, `markdown`, `text`). Default: `auto`
• `url` (string, required): The URL to fetch content from
• `prettyPrint` (boolean, optional): Whether to pretty-print the JSON. Default: `true`
• `url` (string, required): The URL to fetch content from
• `extractText` (boolean, optional): Whether to extract text content only. Default: `false`
• `url` (string, required): The URL to fetch content from
• `url` (string, required): The URL to fetch content from
• HTML sanitization using `sanitize-html` to prevent XSS attacks
• Content validation before processing
• Error handling and safe defaults
• Input parameter validation with Zod
• Safe output encoding
• **Connection errors**: Verify that the URL is accessible and correctly formatted
• **Conversion errors**: Some complex content may not convert cleanly between formats
• **Cross-origin issues**: Some websites may block requests from unknown sources
• Built with the [Model Context Protocol](https://modelcontextprotocol.io/)
• Uses modern, actively maintained libraries with security focus
• Sanitization approach based on OWASP recommendations