fetcher-mcp

694
browser_automation

Fetcher MCP is an MCP server designed for fetching web page content using the Playwright headless browser. It supports handling dynamic web content, intelligent content extraction, and offers flexible output formats like HTML and Markdown. It is optimized for performance, including features like parallel processing and robust error handling.

Fetcher MCP

MCP server for fetch web page content using Playwright headless browser.

Advantages

  • JavaScript Support: Capable of handling dynamic web content using Playwright.
  • Intelligent Content Extraction: Utilizes Readability algorithm to extract main content.
  • Flexible Output Format: Supports HTML and Markdown outputs.
  • Parallel Processing: Enhances efficiency with simultaneous fetching of multiple URLs.
  • Resource Optimization: Blocks unnecessary resources for improved performance.
  • Robust Error Handling: Comprehensive error handling and logging for reliable operation.
  • Configurable Parameters: Allows control over timeouts, content extraction, and more.

Quick Start

  • Run with npx for fast setup.
  • Supports HTTP and SSE transport for flexible connectivity.

Docker Deployment

  • Simple set-up with Docker and Docker Compose for deployment.

Features

  • fetch_url and fetch_urls for single and batch URL fetching with Playwright.