@jharding_npm/server-moz-readability
v1.0.1
Published
Fetch just the main content and convert it to markdown. Strips away all the junk, which is cleaner for LLMs and reduces your overall context window.
Downloads
26
Readme
Mozilla Readability Parser MCP Server (Fork)
This is a fork of the original Mozilla Readability Parser MCP Server, published as @jharding_npm/server-moz-readability.
Now written in TypeScript.
An model context protocol (MCP) server that extracts and transforms webpage content into clean, LLM-optimized Markdown. Returns article title, main content, excerpt, byline and site name. Uses Mozilla's Readability algorithm to remove ads, navigation, footers and non-essential elements while preserving the core content structure. More about MCP.
Current version: 1.0.10
Features
- Removes ads, navigation, footers and other non-essential content
- Converts clean HTML into well-formatted Markdown (also uses Turndown)
- Returns article metadata (title, excerpt, byline, site name)
- Handles errors gracefully
Why Not Just Fetch?
Unlike simple fetch requests, this server:
- Extracts only relevant content using Mozilla's Readability algorithm
- Eliminates noise like ads, popups, and navigation menus
- Reduces token usage by removing unnecessary HTML/CSS
- Provides consistent Markdown formatting for better LLM processing
- Includes useful metadata about the content
Installation
Installing via Smithery
To install Mozilla Readability Parser for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @jharding_npm/server-moz-readability --client claudeManual Installation
npm install @jharding_npm/server-moz-readabilityStarting the Server (CLI)
You can start the server directly with:
npx -y @jharding_npm/server-moz-readabilityYou should see a banner with the version number, and the server will wait for requests via stdio.
Tool Reference
parse
Fetches and transforms webpage content into clean Markdown.
Arguments:
{
"url": {
"type": "string",
"description": "The website URL to parse",
"required": true
}
}Returns:
{
"title": "Article title",
"content": "Markdown content...",
"metadata": {
"excerpt": "Brief summary",
"byline": "Author information",
"siteName": "Source website name"
}
}Usage with Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"readability": {
"command": "npx",
"args": ["-y", "@jharding_npm/server-moz-readability"]
}
}
}Example MCP config.json
To use this server with an MCP host or compatible LLM tool, add it to your MCP config JSON like so:
{
"mcpServers": {
"readability": {
"command": "npx",
"args": ["-y", "@jharding_npm/server-moz-readability"]
}
}
}Save this as config.json and provide it to your MCP host or LLM tool as needed. This will launch the server using npx and make it available for tool calls under the name readability.
Dependencies
- @mozilla/readability - Content extraction
- turndown - HTML to Markdown conversion
- jsdom - DOM parsing
- axios - HTTP requests
License
MIT
