Fetch Browser
A powerful headless browser MCP server that enables AI agents to fetch web content and perform Google searches without requiring any API keys. Built with modern web standards and designed for seamless integration with AI platforms.
Features
- **No API Keys Required**: Uses a sophisticated headless browser approach to fetch content directly
- **Smart Google Search**: - Extract structured results from Google searches - Support for both web and news results - Configurable number of results (1-100) - Full content fetching of search results - Automatic retry and error handling
- **Universal Content Fetching**: - Support for any webpage or API endpoint - Multiple output formats (HTML, JSON, Text, Markdown) - Automatic content type detection - Response size limits and timeout protection - Rate limiting protection
- **Format Conversion**: - Clean HTML to Markdown conversion - Pretty-printed JSON responses - Structured HTML output - Plain text with proper formatting
Tools
1. Google Search Tool (`google_search`)
Executes Google searches and fetches full content of results:
2. URL Fetcher Tool (`fetch_url`)
Fetches content from any URL:
Installation
Via Smithery
Manual Installation
Development
Response Formats
1. Markdown Format
2. JSON Format
3. HTML Format
4. Text Format
Error Handling
- Automatic retries with exponential backoff
- Rate limiting protection
- Timeout handling
- Detailed error messages
- Individual result error tracking
Security Features
- Response size limits
- Request timeouts
- Rate limiting protection
- No API keys or secrets required
- Proper error handling
Credits
**Created by Seth Rose**:
- **Website**: [https://www.sethrose.dev](https://www.sethrose.dev)
- ** (Twitter)**: [https://x.com/TheSethRose](https://x.com/TheSethRose)
- ** (Bluesky)**: [https://bsky.app/profile/sethrose.dev](https://bsky.app/profile/sethrose.dev)
License
MIT License - See [LICENSE](LICENSE) for details