Trafilatura MCP Server

Example Use Cases

• 1

  Extract main textual content from web pages programmatically.

• 2

  Retrieve metadata such as title, author, and publication date from URLs.

• 3

  That require configurable web scraping with options to include or exclude comments and tables.

Description

This MCP server leverages the Trafilatura library to perform web scraping and metadata extraction from URLs. It offers configurable options to include or exclude comments and tables, and exposes a simple asynchronous tool called 'fetch_and_extract' for easy integration. Designed for compatibility with MCP clients, it facilitates programmatic access to web content extraction without requiring API keys or complex setup.