Web Content Extractor

Overview

Web Content Extractor is a Model Context Protocol server that extracts and processes web content into clean, structured formats optimized for LLMs. By integrating with MCP, it lets AI assistants access web extraction tools directly without manual data transfer between applications.

The server runs locally on your machine via the npm package @agenson-horrowitz/web-content-extractor-mcp, communicating over stdio. No authentication is required—it works immediately after installation. Version v1.0.8 is available under the MIT license, with source code hosted at agenson-tools/web-content-extractor-mcp on GitHub.

Web Content Extractor is listed in the AI & Agents category and works with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. Maintainers are invited to claim this listing to verify ownership, receive the Verified badge, and keep information current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "web_content_extractor": {
      "command": "npx",
      "args": [
        "-y",
        "@agenson-horrowitz/web-content-extractor-mcp"
      ]
    }
  }
}