Used for HTML parsing during web crawling, allowing the MCP server to extract and process web content from documentation sites
Provides capabilities for processing Flutter documentation sites, with an example specifically mentioning Flutter Shadcn UI documentation crawling
Transforms web content into clean, structured markdown files optimized for AI consumption and analysis
Serves as the runtime environment for the MCP server, with requirements specifying Node.js 18+ for operation
Mentioned as a use case for processing framework documentation, converting React docs into clean, structured markdown for AI consumption
Used as the implementation language for the MCP server, providing type safety and modern JavaScript features
Better Fetch - Advanced Web Content MCP Server
A powerful Model Context Protocol (MCP) server that intelligently fetches and processes web content with nested URL crawling capabilities. Transform any documentation site or web resource into clean, structured markdown files perfect for AI consumption and analysis.
🚀 Key Features
🕸️ Smart Web Crawling
Nested URL Fetching: Automatically discovers and crawls linked pages up to configurable depth
Single Page Mode: Option for simple single-page content extraction
Domain Filtering: Stay within the same domain or allow cross-domain crawling
Pattern Matching: Include/exclude URLs based on regex patterns
🧠 Intelligent Content Processing
Content Cleaning: Removes ads, navigation, scripts, and other noise automatically
Smart Section Detection: Identifies main content areas (
<main>
,<article>
,.content
)Automatic Titles: Generates meaningful section headers based on page titles and URL structure
Table of Contents: Creates organized TOC with proper nesting
📝 Advanced Markdown Generation
Clean Formatting: Converts HTML to well-structured markdown
Code Block Preservation: Maintains formatting for code snippets and technical content
Link Preservation: Keeps all important links with proper markdown syntax
Metadata Integration: Includes source URLs, generation timestamps, and site information
⚙️ Highly Configurable
Crawl Depth Control: Set maximum levels to crawl (default: 2)
Page Limits: Control maximum pages to process (default: 50)
Timeout Settings: Configurable request timeouts
Respectful Crawling: Built-in delays between requests
Error Handling: Graceful handling of failed requests and invalid URLs
📋 Available Tools
1. fetch_website_nested
Comprehensive web crawling with nested URL processing.
Parameters:
url
(required): Starting URL to crawlmaxDepth
(optional, default: 2): Maximum crawl depthmaxPages
(optional, default: 50): Maximum pages to processsameDomainOnly
(optional, default: true): Restrict to same domainexcludePatterns
(optional): Array of regex patterns to excludeincludePatterns
(optional): Array of regex patterns to includetimeout
(optional, default: 10000): Request timeout in milliseconds
2. fetch_website_single
Simple single-page content extraction.
Parameters:
url
(required): URL to fetchtimeout
(optional, default: 10000): Request timeout in milliseconds
💡 Use Cases
📚 Documentation Processing
API Documentation: Convert REST API docs, SDK guides, and technical references
Framework Docs: Process React, Vue, Angular, or any framework documentation
Library Guides: Extract comprehensive guides from library documentation sites
Tutorial Series: Gather multi-part tutorials into single organized documents
🔍 Content Analysis & Research
Competitive Analysis: Gather competitor documentation and feature descriptions
Market Research: Extract product information from multiple related pages
Academic Research: Collect and organize web-based research materials
Knowledge Base Creation: Transform scattered web content into structured knowledge bases
🤖 AI Training & Context
LLM Context Preparation: Create clean, structured content for AI model training
RAG System Input: Generate high-quality documents for Retrieval-Augmented Generation
Chatbot Knowledge: Build comprehensive knowledge bases for customer service bots
Content Summarization: Prepare web content for automated summarization tasks
🛠️ Installation & Setup
Installing via Smithery
To install Better Fetch for Claude Desktop automatically via Smithery:
Prerequisites
Node.js 18+
npm or yarn
MCP-compatible client (Claude Desktop, VS Code with MCP extension, etc.)
Step 1: Clone and Install
Step 2: Build the Project
Step 3: Test the Server (Optional)
Step 4: Configure Your MCP Client
For Claude Desktop:
Add to your claude_desktop_config.json
:
For VS Code MCP Extension:
For Custom MCP Client:
📖 Usage Examples
Basic Documentation Crawling
Advanced Configuration
Single Page Extraction
📄 Sample Output
The server generates comprehensive markdown files with the following structure:
For a complete example, refer to output.md
which demonstrates the server's output when processing a real documentation site.
🔧 Development
Project Structure
Available Scripts
Testing Your Changes
🚦 Performance & Limits
Default Limits
Max Depth: 2 levels (configurable)
Max Pages: 50 pages (configurable)
Request Timeout: 10 seconds (configurable)
Crawl Delay: 500ms between requests (respectful crawling)
Performance Tips
Set appropriate
maxPages
limits for large sitesUse
includePatterns
to focus on relevant contentEnable
sameDomainOnly
to avoid external link crawlingAdjust
timeout
based on target site response times
🤝 Contributing
We welcome contributions! Please see our Contributing Guide for details.
Development Setup
Fork the repository
Create a feature branch:
git checkout -b feature/amazing-feature
Make your changes and add tests
Commit your changes:
git commit -m 'Add amazing feature'
Push to the branch:
git push origin feature/amazing-feature
Open a Pull Request
📜 License
This project is licensed under the MIT License - see the LICENSE file for details.
🆘 Support & Issues
Bug Reports: GitHub Issues
Feature Requests: GitHub Discussions
Documentation: Check the Wiki
🙏 Acknowledgments
Built with the Model Context Protocol SDK
Powered by Cheerio for HTML parsing
Markdown conversion by Turndown
Made with ❤️ for the AI and developer community
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
A Model Context Protocol server that intelligently fetches and processes web content, transforming websites and documentation into clean, structured markdown with nested URL crawling capabilities.
Related MCP Servers
- AsecurityAlicenseAqualityA Model Context Protocol server that provides web content fetching and conversion capabilities.Last updated -4523MIT License
- AsecurityFlicenseAqualityA Model Context Protocol server that provides tools for fetching and posting HTTP data, with built-in prompts for URL summarization and API analysis.Last updated -2
- -securityAlicense-qualityA Model Context Protocol server that enables web scraping, crawling, and content extraction capabilities through integration with Firecrawl.Last updated -828,887MIT License
- AsecurityAlicenseAqualityA Model Context Protocol server that provides web content fetching capabilities with robots.txt checking removed, allowing LLMs to retrieve and convert web content to markdown.Last updated -2MIT License