Mozilla Readability

Extracts webpage content using Mozilla Readability and outputs clean Markdown with metadata for LLM processing.

dockerfile

16

GitHub Stars

dockerfile

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

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

This MCP server uses Mozilla Readability to extract the main article content from a webpage and transform it into clean, Markdown-friendly text. It returns the article title, content, excerpt, byline, and site name, while removing ads, navigation, and other noise to improve downstream processing by large language models.

How to use

You can send a URL to the parser and receive a structured Markdown representation of the article, including metadata like the title, excerpt, byline, and site name. The server focuses on the readable content and formats it for easy consumption by your MCP client.

The tool exposes a parse operation that accepts a single input URL and returns a JSON payload with the core content and metadata.

{
  "url": "https://example.com/article"
}

How to install

Prerequisites: you need Node.js and npm installed on your system to install and run the MCP server.

npm install server-moz-readability

If you prefer a streamlined setup via a client utility, you can install the MCP server for a Claude Desktop client with this command.

npx -y @smithery/cli install server-moz-readability --client claude

Additional notes

Usage with Claude Desktop is configured by adding the MCP server to your claude_desktop_config.json under mcpServers. The example shows starting the server via a local command.

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

Examples and tool reference

The primary tool you’ll interact with is parse, which fetches and transforms a webpage into Markdown and metadata.

{
  "title": "Article title",
  "content": "Markdown content...",
  "metadata": {
    "excerpt": "Brief summary",
    "byline": "Author information",
    "siteName": "Source website name"
  }
}

Available tools

parse

Fetches a webpage URL and transforms it into Markdown content with article metadata (title, excerpt, byline, site name) using Mozilla Readability and Turndown.