mcp-huggingfetch
What is mcp-huggingfetch?
mcp-huggingfetch is a tool designed to speed up the download of models from HuggingFace. It supports concurrent downloads, resume capabilities, and intelligent retry mechanisms, making it 3-5 times faster than traditional methods. This tool is compatible with various clients including Claude Desktop, Claude Code, Cursor, and VS Code.
Benefits
- Faster Downloads: mcp-huggingfetch significantly accelerates the download process, making it 3-5 times faster than traditional methods.
- Concurrent Downloading: Supports downloading multiple files at the same time, saving time and effort.
- Resume Capabilities: Allows you to resume interrupted downloads, ensuring you don't have to start over.
- Intelligent Retry Mechanisms: Automatically retries failed downloads, increasing the chances of successful downloads.
- Wide Compatibility: Works with popular clients like Claude Desktop, Claude Code, Cursor, and VS Code.
Use Cases
- Researchers and Developers: Quickly download large models for AI research and development.
- AI Enthusiasts: Easily access and experiment with various AI models.
- Educational Institutions: Facilitate the download of models for teaching and learning purposes.
Setup Instructions
To set up mcp-huggingfetch, you need to add specific configurations to your client's settings. Here are the steps for different clients:
Claude Desktop
Add the following to yourclaude_desktop_config.json:
{"mcpServers":{"huggingfetch":{"command":"npx","args":["-y","mcp-huggingfetch@latest"],"env":{"HUGGINGFACE_TOKEN":"your_token_here"}}}}Claude Code
Add the following to your.claude/claude_config.json:
{"mcpServers":{"huggingfetch":{"command":"npx","args":["-y","mcp-huggingfetch@latest"],"env":{"HUGGINGFACE_TOKEN":"your_token_here"}}}}Cursor / VS Code (Continue Extension)
Add the following to yourconfig.json:
{"mcp":[{"name":"huggingfetch","command":"npx","args":["-y","mcp-huggingfetch@latest"],"env":{"HUGGINGFACE_TOKEN":"your_token_here"}}]}Usage
After configuration, you can use the following features directly in conversations:
List Files
View repository files before downloading:
List all files in the 2Noise/ChatTTS repositoryShow JSON files in the bert-base-uncased repositoryDisplay files in openai/whisper-large-v3 sorted by sizeDownload Models
Selectively download required files:
Please download the ChatTTS model to ./models directoryDownload microsoft/DialoGPT-medium model, only .bin filesDownload openai/whisper-large-v3 model, exclude test filesSupported Features
List Tool Options (list_huggingface_files)
| Parameter | Type | Description | Example |
|---|---|---|---|
repo_id | string | HuggingFace repository ID | "2Noise/ChatTTS" |
revision | string | Git branch/tag | "main","v1.0" |
path | string | Repository sub-path | "models/" |
pattern | string | File name filter pattern | "*.json","*.safetensors" |
sort_by | string | Sort method | "size","name","type" |
Download Tool Options (download_huggingface_model)
| Parameter | Type | Description | Example |
|---|---|---|---|
repo_id | string | HuggingFace repository ID | "2Noise/ChatTTS" |
download_dir | string | Download directory | "./models" |
files | array | Specific file list | ["model.bin", "config.json"] |
allow_patterns | string/array | Include patterns | "*.json"or["*.pt", "*.bin"] |
ignore_patterns | string/array | Exclude patterns | "test_*"or["*.onnx", "test_*"] |
revision | string | Git branch/tag | "main","v1.0" |
force_redownload | boolean | Force re-download | true,false |
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
HUGGINGFACE_TOKEN | - | HuggingFace access token | |
HUGGINGFETCH_DOWNLOAD_DIR | ~/Downloads/huggingface_models | Default download directory | |
HF_HOME | ~/.cache/huggingface | Cache directory | |
LOG_LEVEL | info | Log level (debug,info,warn,error) |
FAQ
Q: Token authentication failed, what should I do?A: Check ifHUGGINGFACE_TOKENis correctly set, ensure the token is valid and has sufficient permissions.
Q: Download speed is slow, what can I do?A: The tool supports resume downloads and concurrent downloading. Network issues may cause slow speeds, automatic retry will occur.
Q: How to download private models?A: Ensure your HuggingFace account has access permissions and use a valid token.
Q: What file formats are supported?A: All file formats on HuggingFace are supported, including.pt,.bin,.safetensors,.json,.txt, etc.
Development
Prerequisites
- Node.js 18+
- npm or yarn
Installation
git clone https://github.com/freefish1218/mcp-huggingfetch.gitcd mcp-huggingfetchnpm installDevelopment Commands
npm run dev # Run with file watchingnpm start # Run the MCP servernpm run test:basic # Run basic functionality testsnpm test # Run Jest unit testsnpm run lint # Check code stylenpm run lint:fix # Auto-fix linting issuesRelease Commands
npm run release:patch # Release patch version (1.0.0 -> 1.0.1)npm run release:minor # Release minor version (1.0.0 -> 1.1.0)npm run release:major # Release major version (1.0.0 -> 2.0.0)The release scripts will automatically:* Run tests and linting* Update version number* Create git tag* Push to GitHub* Publish to npm
Building
npm run build # Build single binarynpm run build:all # Build for all platforms (Linux, macOS, Windows)License
MIT License - see file for details.
Links
- GitHub:https://github.com/freefish1218/mcp-huggingfetch
- Issues:https://github.com/freefish1218/mcp-huggingfetch/issues
- NPM:https://www.npmjs.com/package/mcp-huggingfetch
Contributing
Contributions are welcome! Please seeCONTRIBUTING.mdfor guidelines.
This content is either user submitted or generated using AI technology (including, but not limited to, Google Gemini API, Llama, Grok, and Mistral), based on automated research and analysis of public data sources from search engines like DuckDuckGo, Google Search, and SearXNG, and directly from the tool's own website and with minimal to no human editing/review. THEJO AI is not affiliated with or endorsed by the AI tools or services mentioned. This is provided for informational and reference purposes only, is not an endorsement or official advice, and may contain inaccuracies or biases. Please verify details with original sources.
Comments
Please log in to post a comment.