URL Content Extractor MCP Server

A Model Context Protocol server that extracts content from URLs and provides properly formatted citations. Perfect for AI assistants that need to access and cite web content.

🚀 Quick Start

Install and Run with uvx/npx

# Run directly with uvx (recommended)
uvx url-content-extractor-mcp

# Or with npx
npx url-content-extractor-mcp

Install Globally

npm install -g url-content-extractor-mcp
url-content-extractor-mcp

🔌 MCP Client Configuration

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "url-content-extractor": {
      "command": "uvx",
      "args": ["url-content-extractor-mcp"]
    }
  }
}

Continue.dev

Add to your MCP configuration:

{
  "mcpServers": {
    "url-content-extractor": {
      "command": "npx",
      "args": ["url-content-extractor-mcp"]
    }
  }
}

🛠️ Features

• Multiple URL processing: Extract content from multiple URLs in one call
• Citation formats: APA, MLA, and Simple citation styles
• Smart content extraction: Focuses on main content, removes navigation/ads
• Domain filtering: Allow/block specific domains for security
• Metadata extraction: Title, author, publication date, description
• Error handling: Graceful handling of failed URLs
• TypeScript: Full type safety and modern JavaScript features

📖 Usage

The server provides one tool: extract_url_content

Single URL

Extract content from: https://example.com/article

Multiple URLs

Compare these articles: https://site1.com/news, https://site2.com/blog

Example Output

🌐 Web Content Extraction Results

Processed: 1 successful, 0 failed

## 📄 Extracted Content

**📄 Document 1: Breaking News Article**

**Source:** https://example.com/article
**Domain:** example.com
**Author:** Jane Reporter
**Published:** 2024-07-04
**Citation:** Jane Reporter. Breaking News Article. https://example.com/article

**Content:**
[Full article content here...]

## 📖 Citation Summary

1. Jane Reporter. Breaking News Article. https://example.com/article

⚙️ Configuration

The server includes sensible defaults but can be customized by modifying the source:

• Max content length: 15,000 characters
• Min content length: 500 characters
• Timeout: 15 seconds
• Max URLs per call: 5
• Citation style: Simple (configurable to APA/MLA)
• Blocked domains: localhost, 127.0.0.1, 0.0.0.0

🔒 Security

• Domain filtering prevents access to local/internal resources
• Request timeouts prevent hanging
• Content length limits prevent memory issues
• No execution of JavaScript from scraped pages

📋 Requirements

• Node.js 18.0.0 or higher
• Internet connection for URL fetching

🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Submit a pull request

📄 License

MIT License - see LICENSE file for details.

🐛 Issues

Report issues on GitHub Issues.

🔗 Links

• Model Context Protocol
• GitHub Repository
• NPM Package