Hub Semantic Search MCP

🚀 Hugging Face Hub Semantic Search MCP Server

An MCP server that offers semantic search capabilities for Hugging Face models and datasets, enabling MCP - compatible clients to explore the Hugging Face ecosystem with natural language queries.

🚀 Quick Start

No installation needed! UV will automatically fetch and run the server. However, you need UV (a fast Python package installer) and Claude Desktop or another MCP - compatible client.

✨ Features

• Semantic Search: AI - powered similarity search (not just keyword matching).
• Dataset Search: Find datasets based on natural language descriptions.
• Model Search: Find models with optional parameter count filtering.
• Similarity Search: Find similar models/datasets to a given one.
• Trending Content: Get currently trending models and datasets.
• Detailed Metadata: Access comprehensive technical information via HuggingFace API.
• Model/Dataset Cards: Download README cards for detailed information.

📦 Installation

Prerequisites

• UV - Fast Python package installer
• Claude Desktop or another MCP - compatible client

💻 Usage Examples

Basic Usage

Once configured, you can use the tools in Claude Desktop:

# Search for Datasets
> "Find datasets about climate change and weather patterns"

# Search for Models
> "Find small language models under 1B parameters for text generation"

# Find Similar Content
> "Find datasets similar to 'squad' for question answering"

# Get Trending Content
> "Show me the top 10 trending AI models this week"

# Get Detailed Metadata
> "Get detailed information about the 'stanford - nlp/imdb' dataset"
> "Show me technical details and configuration for 'microsoft/DialoGPT - medium'"
> "What's the parameter count and architecture of 'microsoft/DialoGPT - medium'?"

# Download Documentation
> "Download the model card for 'microsoft/DialoGPT - medium'"

📚 Documentation

Configuration

Claude Desktop Setup

Add the following to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "huggingface - hub - search": {
      "command": "uvx",
      "args": [
        "git+https://github.com/davanstrien/hub - semantic - search - mcp.git"
      ],
      "env": {
        "HF_SEARCH_API_URL": "https://davanstrien - huggingface - datasets - search - v2.hf.space"
      }
    }
  }
}

Alternative: Local Development Setup

If you want to contribute or modify the code:

# Clone the repository
git clone https://github.com/davanstrien/hub - semantic - search - mcp.git
cd hub - semantic - search - mcp

# Install dependencies with UV
uv sync

Then configure Claude Desktop to use the local version:

{
  "mcpServers": {
    "huggingface - hub - search": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/hub - semantic - search - mcp",
        "run",
        "python",
        "app.py"
      ],
      "env": {
        "HF_SEARCH_API_URL": "https://davanstrien - huggingface - datasets - search - v2.hf.space"
      }
    }
  }
}

Environment Variables

• HF_SEARCH_API_URL: Base URL for the search API (default: https://davanstrien - huggingface - datasets - search - v2.hf.space)

Search Backend

This MCP server connects to a semantic search API that indexes Hugging Face models and datasets with AI - generated summaries. The search uses embedding - based similarity rather than keyword matching, making it more effective for discovering relevant content based on intent and meaning.

Development

Running Locally

# Run the server directly
uv run python app.py

# Or activate the virtual environment
uv shell
python app.py

Testing with MCP Inspector

# Test the GitHub version
npx @modelcontextprotocol/inspector uvx git+https://github.com/davanstrien/hub - semantic - search - mcp.git

# Or test locally
npx @modelcontextprotocol/inspector uv run python app.py

Contributing

Contributions are welcome! Please feel free to submit issues and pull requests.

Development Setup

git clone https://github.com/davanstrien/hub - semantic - search - mcp.git
cd hub - semantic - search - mcp
uv sync --dev

📄 License

MIT License - see LICENSE file for details.

Related Projects

• Model Context Protocol
• Hugging Face Hub
• Claude Desktop
• UV - Fast Python package installer

⚠️ Important Note

This is an unofficial MCP server inspired by Hugging Face's official MCP server. It may be deprecated at any time if official functionality supersedes it. For the official server, see hf.co/mcp.