Mozilla Readability Parser

Mozilla Readability Parser is an MCP server that extracts core webpage content and transforms it into clean, LLM-optimized Markdown using Mozilla's Readability algorithm. The tool connects to live web URLs through Axios and JSDOM, strips away non-essential web elements such as advertisements, navigation menus, and footers, and processes the remaining HTML into structured Markdown via Turndown. Software engineers, researchers, and AI developers use this server to retrieve articles, documentation, and web pages without burning context tokens on styling, scripts, or interface boilerplate. By returning structured metadata alongside the parsed text—including titles, excerpts, bylines, and site names—the server enables language models to ingest and summarize external web articles with minimal noise and maximum contextual accuracy.

Category: Browser & Web Automation

Tags: content extraction, markdown, parsing, readability, web scraping

Visit Mozilla Readability Parser

How to install and configure Mozilla Readability Parser

1. Open your Claude Desktop configuration file (claude_desktop_config.json). 2. Add the Mozilla Readability Parser configuration to the mcpServers object: json { "mcpServers": { "readability": { "command": "npx", "args": ["-y", "server-moz-readability"] } } } 3. Alternatively, install the package automatically via Smithery by running npx -y @smithery/cli install server-moz-readability --client claude or manually with npm install server-moz-readability. 4. Restart Claude Desktop to start using the parse tool.

What you can do with Mozilla Readability Parser

• Parsing lengthy online documentation and articles into compact Markdown to conserve context tokens during AI analysis. - Extracting article text, author bylines, and site metadata directly into Claude for research and reference compilation. - Stripping advertisements, popups, and navigation sidebars from news reports prior to automated text summarization. - Converting messy web pages into clean Markdown formatting for retrieval-augmented generation pipelines and knowledge bases.

Key facts

• Open Source
• https://github.com/mozilla/readability
• Browser & Web Automation, Files, Documents & PDFs
• content extraction, markdown, parsing, readability, web scraping

Part of MCP Servers

How do I install Mozilla Readability Parser?

You can configure it directly in Claude Desktop by adding an npx entry running server-moz-readability inside claude_desktop_config.json. Alternatively, you can use the Smithery CLI with the command npx -y @smithery/cli install server-moz-readability --client claude, or install it via npm using npm install server-moz-readability.

What can Mozilla Readability Parser do?

The server exposes a parse tool that takes a target URL, strips away ads, navigation elements, and footers, and outputs clean Markdown. Along with the core text, it extracts article metadata including the page title, excerpt summary, author byline, and source site name.

Which MCP clients work with Mozilla Readability Parser?

It is designed to work with Claude Desktop through its standard configuration file, as well as any other Model Context Protocol client capable of invoking NPX commands and communicating over standard input and output.

Is Mozilla Readability Parser open source?

Yes, Mozilla Readability Parser is open source software released under the MIT license. You can inspect its source code and underlying dependencies such as Turndown, JSDOM, and Mozilla Readability.