mcp-file-downloader

The MCP File Downloader server enables Claude Desktop to fetch files from the web by first attempting a direct HTTP download and, if needed, automatically switching to a browser-based approach using Playwright to render JavaScript-heavy sites. It supports smart redirect handling (up to 10 levels) and flexible file naming, so you can save files with their original names or specify a custom name. This makes it suitable for downloading datasets, documents, or any file that may be behind redirects or require browser interaction.

Prerequisites:

• Node.js 18+ installed on your system
• Claude Desktop configured to use MCP servers

Installation steps:

1. Clone the repository:

git clone https://github.com/yourusername/mcp-file-downloader.git
cd mcp-file-downloader

2. Install dependencies:

npm install

3. Run the MCP server locally (example):

npx ts-node-dev download-server.js

4. Add to Claude Desktop config with the appropriate path to the running server, for example:

Windows:

"mcpServers": {
  "file-downloader": {
    "command": "node",
    "args": ["C:\\path\\to\\mcp-file-downloader\\download-server.js"]
  }
}

5. Restart Claude Desktop to pick up the new MCP server configuration.

Tips and common issues:

• Ensure Node.js has write permissions to the download directory used by the server.
• If you encounter a “Too many redirects” error, prefer a request with use_browser set to true, since the site may require JavaScript rendering.
• The server uses Playwright for browser automation; ensure any required browsers are installed or allow the server to install them on first run.
• Check that Claude Desktop configuration paths match your operating system (Windows vs macOS/Linux paths differ).
• If downloads fail intermittently, verify network access, permissions, and that the target URL is reachable from the host running the MCP server.