webscraper

webscraper
Certified

4.0

Webscraper MCP is an MCP server designed for Claude desktop, enabling it to scrape text from websites, YouTube transcripts, and PDFs.

Webscraper MCP is a powerful tool for Claude desktop users, allowing seamless extraction of text content from various online sources. By simply providing a link, users can obtain text from standard web pages, YouTube videos, and PDF documents. This functionality is particularly useful for users who need to gather information from diverse sources quickly and efficiently. The server is designed to handle different types of content, ensuring that users can access the information they need without manual intervention. Whether it's extracting a transcript from a YouTube video or converting a PDF to markdown text, Webscraper MCP simplifies the process, making it accessible and user-friendly.

Features

  • Extracts text from standard web pages using provided URLs.
  • Converts PDF documents to markdown text for easy readability.
  • Retrieves transcripts from YouTube videos for content analysis.
  • Supports a wide range of online content types for comprehensive data extraction.
  • User-friendly interface for seamless integration with Claude desktop.

MCP Tools

  • get_pdf: Convert a URL that leads to a PDF file to markdown text.
  • get_webpage_content: Returns the text content on a webpage based on the link provided.
  • get_youtube_transcript: Extracts the transcript from a YouTube video.

Usage with Different Platforms

Claude Desktop

mcp: {
  "get_webpage_content": "https://example.com",
  "get_pdf": "https://example.com/document.pdf",
  "get_youtube_transcript": "https://youtube.com/watch?v=example"
}