Website Downloader MCP Server

Website Downloader MCP Server

Download and archive entire websites as local, browsable directories via MCP.

144
Stars
29
Forks
144
Watchers
3
Issues
Website Downloader MCP Server provides a Model Context Protocol (MCP) compatible server that enables users to download entire websites using wget. It preserves the website structure, rewrites internal links for local browsing, and allows for custom download depth and output directories. The server is intended for integration into larger systems or AI workflows that utilize MCP servers. Installation instructions and usage examples are provided for multiple platforms.

Key Features

Full website download using wget
Preserves internal link structure for offline browsing
Customizable download depth
Configurable output directory
Includes all page requisites such as CSS and images
Restricts downloads to the same domain
Automatic file extension management
Integration via MCP server protocol
Cross-platform usage instructions
Easily added to MCP server settings

Use Cases

Creating offline archives of websites for research or backup
Enabling local browsing of web resources for AI model context ingestion
Automating static website downloads in workflow pipelines
Facilitating legal discovery or evidence preservation workflows
Supporting AI systems requiring up-to-date web content snapshots
Educational purposes to capture and demonstrate site structure
Ensuring long-term access to changing or disappearing websites
Testing web application behavior in air-gapped environments
Integrating into larger model-context-aware systems
Bulk downloading of sites for analysis or compliance

README

Website Downloader MCP Server

This MCP server provides a tool to download entire websites using wget. It preserves the website structure and converts links to work locally.

Prerequisites

The server requires wget to be installed on your system.

Installing wget

macOS

Using Homebrew:

bash
brew install wget

Linux (Debian/Ubuntu)

bash
sudo apt-get update
sudo apt-get install wget

Linux (Red Hat/Fedora)

bash
sudo dnf install wget

Windows

  1. Using Chocolatey:
bash
choco install wget
  1. Or download the binary from: https://eternallybored.org/misc/wget/
    • Download the latest wget.exe
    • Place it in a directory that's in your PATH (e.g., C:\Windows\System32)

Usage

The server provides a tool called download_website with the following parameters:

  • url (required): The URL of the website to download
  • outputPath (optional): The directory where the website should be downloaded. Defaults to the current directory.
  • depth (optional): Maximum depth level for recursive downloading. Defaults to infinite. Set to 0 for just the specified page, 1 for direct links, etc.

Example

json
{
  "url": "https://example.com",
  "outputPath": "/path/to/output",
  "depth": 2  // Optional: Download up to 2 levels deep
}

Features

The website downloader:

  • Downloads recursively with infinite depth
  • Includes all page requisites (CSS, images, etc.)
  • Converts links to work locally
  • Adds appropriate extensions to files
  • Restricts downloads to the same domain
  • Preserves the website structure

Installation

  1. Build the server:
bash
npm install
npm run build
  1. Add to MCP settings:
json
{
  "mcpServers": {
    "website-downloader": {
      "command": "node",
      "args": ["/path/to/website-downloader/build/index.js"]
    }
  }
}

Star History

Star History Chart

Repository Owner

pskill9
pskill9

User

Repository Details

Language JavaScript
Default Branch main
Size 9 KB
Contributors 3
MCP Verified Nov 12, 2025

Programming Languages

JavaScript
100%

Tags

Join Our Newsletter

Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.

We respect your privacy. Unsubscribe at any time.

Related MCPs

Discover similar Model Context Protocol servers

  • mcp-read-website-fast

    mcp-read-website-fast

    Fast, token-efficient web content extraction and Markdown conversion for AI agents.

    Provides a Model Context Protocol (MCP) compatible server that rapidly fetches web pages, removes noise, and converts content to clean Markdown with link preservation. Designed for local use by AI-powered tools like IDEs and large language models, it offers optimized token usage, concurrency, polite crawling, and smart caching. Integrates with Claude Code, VS Code, JetBrains IDEs, Cursor, and other MCP clients.

    • 111
    • MCP
    • just-every/mcp-read-website-fast
  • Urlbox MCP Server

    Urlbox MCP Server

    Screenshot, PDF, HTML, and markdown generation MCP for websites.

    Urlbox MCP Server enables AI clients to generate website screenshots, PDFs, and extract HTML or markdown from web pages via the Urlbox Screenshot API. It supports automated extraction of metadata, cookies, and allows local file downloads. The server is designed to be integrated with LLMs, which can use its tools to capture and process web content on demand via standardized MCP interfaces. Environment variable configuration secures API access, and multiple formats are supported for flexible output.

    • 1
    • MCP
    • urlbox/urlbox-mcp-server
  • WebScraping.AI MCP Server

    WebScraping.AI MCP Server

    MCP server for advanced web scraping and AI-driven data extraction

    WebScraping.AI MCP Server implements the Model Context Protocol to provide web data extraction and question answering functionalities. It integrates with WebScraping.AI to offer robust tools for retrieving, rendering, and parsing web content, including structured data and natural language answers from web pages. It supports JavaScript rendering, proxy management, device emulation, and custom extraction configurations, making it suitable for both individual and team deployments in AI-assisted workflows.

    • 33
    • MCP
    • webscraping-ai/webscraping-ai-mcp-server
  • Scrapeless MCP Server

    Scrapeless MCP Server

    A real-time web integration layer for LLMs and AI agents built on the open MCP standard.

    Scrapeless MCP Server is a powerful integration layer enabling large language models, AI agents, and applications to interact with the web in real time. Built on the open Model Context Protocol, it facilitates seamless connections between models like ChatGPT, Claude, and tools such as Cursor to external web capabilities, including Google services, browser automation, and advanced data extraction. The system supports multiple transport modes and is designed to provide dynamic, real-world context to AI workflows. Robust scraping, dynamic content handling, and flexible export formats are core parts of the feature set.

    • 57
    • MCP
    • scrapeless-ai/scrapeless-mcp-server
  • Fetcher MCP

    Fetcher MCP

    Intelligent web content fetching and extraction using Playwright.

    Fetcher MCP is a server that fetches and extracts web page content using the Playwright headless browser while supporting the Model Context Protocol. It intelligently processes dynamic web pages with JavaScript, employs the Readability algorithm to extract main content, and supports output in both HTML and Markdown formats. Designed for seamless integration with AI model environments, it offers robust parallel processing, resource optimization, and flexible deployment options including Docker.

    • 906
    • MCP
    • jae-jae/fetcher-mcp
  • Markdownify MCP Server

    Markdownify MCP Server

    Convert diverse files and web content into Markdown via the Model Context Protocol.

    Markdownify MCP Server offers a protocol-based server that transforms various file types—including PDF, images, audio, DOCX, XLSX, and PPTX—as well as web content like YouTube videos, Bing search results, and web pages into Markdown format. The server exposes a suite of conversion tools through a standardized interface for easy integration with applications. Optional configuration allows retrieval of Markdown files from restricted directories, and the platform supports development customization for additional tool integration. Deployment and operation are straightforward with cross-platform support (with pending Windows improvements).

    • 2,256
    • MCP
    • zcaceres/markdownify-mcp
  • Didn't find tool you were looking for?

    Be as detailed as possible for better results