fetcher-mcp

fetcher-mcp

4.2

If you are the rightful owner of fetcher-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcpreview.com.

Fetcher MCP is a server designed to fetch web page content using the Playwright headless browser.

Fetcher MCP is a Model Context Protocol (MCP) server that leverages the Playwright headless browser to fetch and process web page content. It is particularly adept at handling dynamic web content and modern web applications due to its JavaScript execution capabilities. The server includes features such as intelligent content extraction using a Readability algorithm, flexible output formats in HTML and Markdown, and parallel processing for efficient batch operations. Fetcher MCP also optimizes resource usage by blocking unnecessary elements and includes robust error handling to ensure reliable operation. It is configurable with parameters for timeouts, content extraction, and output formatting, making it versatile for various use cases.

Features

  • JavaScript Support: Executes JavaScript to handle dynamic web content.
  • Intelligent Content Extraction: Uses Readability algorithm to extract main content.
  • Flexible Output Format: Supports HTML and Markdown formats.
  • Parallel Processing: Fetches multiple URLs concurrently.
  • Resource Optimization: Blocks unnecessary resources to save bandwidth.

Tools

  • fetch_url: Retrieve web page content from a specified URL with options for content extraction and output format.
  • fetch_urls: Batch retrieve web page content from multiple URLs in parallel with performance optimization.