Mozilla Readability Parser

Example Use Cases

• 1

  Extract clean, relevant article content from webpages for LLM processing.

• 2

  Convert HTML content into Markdown while removing ads and navigation elements.

• 3

  Article metadata like title, excerpt, byline, and site name alongside the content.

Description

This MCP server fetches webpage content and uses Mozilla's Readability algorithm to remove ads, navigation, footers, and other non-essential elements, preserving the core article structure. It converts the cleaned HTML into well-formatted Markdown and returns useful metadata such as title, excerpt, byline, and site name. This results in reduced token usage and consistent formatting for better processing by large language models.