关于
This Model Context Protocol server provides versatile web content fetching and conversion capabilities, suitable for tasks ranging from simple data extraction to advanced web scraping. It offers tools for retrieving raw text, fully rendered HTML, and converting web content to Markdown, including specialized functions for extracting and summarizing main content from articles and blog posts.
主要功能
- Retrieves raw text content directly from URLs
- Fetches fully rendered HTML content using Playwright
- Converts web content to well-formatted Markdown
- Extracts and converts main content, removing navigation and headers
- Supports tables and definition lists in Markdown conversion
使用案例
- Extracting data from JSON, XML, CSV, or plain text files
- Archiving web content and documentation
- Summarizing articles and blog posts