Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP File Downloader download the PDF from https://example.com/report.pdf as quarterly_report.pdf"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server that enables Claude Desktop to download files from the web, with automatic browser fallback for JavaScript-heavy sites.
Claude Desktop can't natively download files. This MCP server bridges that gap, providing:
Direct HTTP downloads with smart redirect handling
Automatic browser-based fallback for complex sites
Seamless integration with Claude Desktop
Perfect for downloading datasets, documents, and files from sites that use JavaScript for download links.
Related MCP server: WebClone MCP Server
Smart Download Strategy: Tries HTTP first, falls back to browser if needed
10-Level Redirect Support: Handles complex redirect chains
JavaScript Rendering: Uses Playwright for sites requiring browser execution
Flexible File Naming: Auto-names from URL or accepts custom names
Cross-Platform: Works on Windows, macOS, and Linux
Node.js 18+
Claude Desktop
Clone the repository:
git clone https://github.com/yourusername/mcp-file-downloader.git
cd mcp-file-downloaderInstall dependencies:
npm installAdd to Claude Desktop config:
Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"file-downloader": {
"command": "node",
"args": ["C:\\path\\to\\mcp-file-downloader\\download-server.js"]
}
}
}Restart Claude Desktop
In Claude Desktop, you can now download files:
"Download this file: https://example.com/data.csv"
"Get the PDF from https://example.com/report.pdf and save it as quarterly_report.pdf"
"Download https://site-with-javascript.com/dynamic-file.xlsx"
(automatically uses browser if HTTP fails)url (required): The URL to download from
filename (optional): Save as this filename. Can include full path
use_browser (optional): Force browser download method
For sites that always need JavaScript:
"Download https://complex-site.com/file.zip using browser mode""Download https://example.com/data.csv to ~/Documents/mydata.csv"mcp-file-downloader/
āāā download-server.js # MCP server implementation
āāā package.json # Dependencies
āāā LICENSE # MIT license
āāā README.md # This file
āāā CLAUDE_HINTS.md # Advanced documentationContributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.
Fork the repository
Create your feature branch (git checkout -b feature/AmazingFeature)
Commit your changes (git commit -m 'Add some AmazingFeature')
Push to the branch (git push origin feature/AmazingFeature)
Open a Pull Request
The site likely requires JavaScript. Use use_browser: true parameter.
Check that Node.js has write permissions to your download directory.
Verify the path in claude_desktop_config.json is correct
Fully quit Claude Desktop (check system tray)
Restart Claude Desktop
This project is licensed under the MIT License - see the LICENSE file for details.
Built for the Model Context Protocol ecosystem
Uses Playwright for browser automation
Inspired by the need to download ETF holdings data in Claude Desktop
For questions or support, please open an issue on GitHub.
Note: This is an independent project and not officially affiliated with Anthropic or Claude.
Download a file from URL (supports redirects and browser download)
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | URL to download | |
| filename | No | Save as filename (optional). Can be absolute path. | |
| use_browser | No | Force browser download method (for JavaScript-heavy sites). Default: false |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It mentions support for redirects and browser downloads, which adds some behavioral context beyond basic downloading. However, it lacks details on error handling, rate limits, authentication needs, or what happens if the filename isn't specified, leaving significant gaps for a tool that interacts with external URLs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core action. It includes useful features without unnecessary elaboration. However, it could be slightly more structured by separating key points, but overall, it's appropriately sized and wastes no words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations and no output schema, the description is incomplete for a tool that downloads files from URLs. It misses critical details like return values (e.g., file path, success status), error conditions, or security considerations. The schema covers inputs well, but the overall context lacks depth for safe and effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents all parameters. The description adds no additional meaning beyond what's in the schema, such as examples or edge cases. With high schema coverage, the baseline is 3, as the description doesn't compensate but also doesn't detract.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'download' and resource 'file from URL', making the purpose immediately understandable. It distinguishes the tool by mentioning support for redirects and browser downloads, though without sibling tools, differentiation isn't needed. However, it doesn't specify the output format or destination, leaving some ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives or any prerequisites. It mentions 'supports redirects and browser download' as features, but doesn't explain scenarios where these are beneficial, such as handling complex websites or authentication issues. Without sibling tools, this is less critical, but still a gap.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
With only one tool, there is no possibility of confusion or overlap between tools. The tool's purpose is clearly defined as downloading files from URLs, making it perfectly distinct by default.
Since there is only a single tool, naming consistency is inherently perfect. The tool name 'download_file' follows a clear verb_noun pattern, and there are no other tools to compare it against for inconsistency.
A single tool is too few for a server named 'MCP File Downloader', as it suggests a narrow scope that might lack essential operations like listing downloads, checking status, or handling errors. Typically, a downloader would benefit from 3-5 tools for basic functionality.
The tool surface is severely incomplete for a file downloader domain. While 'download_file' covers the core action, there are obvious gaps such as no tools for managing downloads (e.g., cancel, pause, resume), verifying file integrity, or handling authentication, which could lead to agent failures in real-world scenarios.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Reliable web fetching for AI agents with retry, circuit breaker, caching, and anti-bot bypass
Screenshot any URL/HTML as PNG/JPEG/WebP, or read it as clean Markdown/text for LLMs.
Read a URL as clean markdown, screenshot a website, url to PDF. Web access for agents, no signup.
Web scraping for AI agents. Converts URLs to clean, LLM-ready Markdown with anti-bot bypass.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/abs222222/mcp-file-downloader'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
