Mozilla Readability Parser MCP ServerServer

emzimmer
GitHub
Web ScrapingBrowser AutomationAgent Orchestration

💡 Description

This server extracts and transforms webpage content into clean, LLM-optimized Markdown. It returns article title, main content, excerpt, byline, and site name using Mozilla's Readability algorithm to remove ads, navigation, footers, and non-essential elements while preserving the core content structure.

📝 JSON Entries

{
  "mcpServers": [
    {
      "readability": {
        "args": [
          "-y",
          "server-moz-readability"
        ],
        "command": "npx"
      }
    }
  ]
}

🛠️ Tools

parse

Features

  • Removes ads, navigation, footers, and other non-essential content
  • Converts clean HTML into well-formatted Markdown
  • Returns article metadata (title, excerpt, byline, site name)
  • Handles errors gracefully

💬 Example Queries

  • Parse a webpage and extract the main content as Markdown
  • Get the title and byline for the article from a URL