🌼 Heads up

This repo has been a fun little project, and it's pretty cool seeing it hit 70+ stars and 15+ forks, thank you! But I wanted to let anyone new know that DaisyUI has finally released official "Skills" over at daisyui.com/docs/skill/. I now recommend using that one since it's official and, honestly, just better for modern AI models. This repo will still work if you're already using it, but for new projects I'd go with the official skill. I'd at least recommend you check it out and see if it fits your needs better. Thanks again for the support, and happy coding! 🌼

✨ Features

• 🎯 Token-Efficient — Only exposes relevant context via MCP tools, saving precious tokens
• 📚 60+ Components — Full coverage of DaisyUI's component library
• 🔄 Auto-Updatable — Fetch the latest docs anytime with one command
• ✏️ Customizable — Edit or add your own component docs to fit your project
• ⚡ Fast & Lightweight — Built with FastMCP for optimal performance

🛠️ MCP Tools

This server exposes two tools that AI assistants can use:

💡 The component docs are pulled from daisyui.com/llms.txt and stored locally as markdown files. This way you can also add your own custom components or edit existing ones to your liking or project needs.

💬 Example Prompts

Try asking your AI assistant:

"What DaisyUI components are available?"

"Implement a responsive card grid using DaisyUI"

"How does the modal component work? Show me an example"

📦 Installation

1. Clone the repository

git clone https://github.com/birdseyevue/fastmcp.git
cd fastmcp

2. Create a virtual environment (recommended)

python -m venv venv

# Windows
venv\Scripts\activate

# macOS/Linux
source venv/bin/activate

3. Install dependencies

pip install -r requirements.txt

🐳 Docker

You can also run the MCP server using Docker.

Build and run with Docker

docker build -t daisyui-mcp .
docker run -i --rm daisyui-mcp

Using Docker Compose

docker compose up --build

The docker-compose.yml mounts the local components/ directory as a volume, so any changes you make to component docs on the host are reflected inside the container.

Docker configuration for AI assistants

{
  "servers": {
    "daisyui": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "daisyui-mcp"]
    }
  }
}

🚀 Usage

First-time setup

Upon first run, the MCP server will not have any component docs. Fetch them by running:

python update_components.py

This fetches the latest llms.txt from DaisyUI and generates all the markdown files in /components.

Running the server

python mcp_server.py

Updating component docs

If DaisyUI releases new components or updates their docs, simply run:

python update_components.py

⚙️ Configuration

Add the MCP server to your AI assistant's configuration:

{
  "servers": {
    "daisyui": {
      "command": "<path-to-repo>/venv/Scripts/python.exe",
      "args": ["<path-to-repo>/mcp_server.py"]
    }
  }
}

{
  "servers": {
    "daisyui": {
      "command": "C:/Users/username/Downloads/fastmcp/venv/Scripts/python.exe",
      "args": ["C:/Users/username/Downloads/fastmcp/mcp_server.py"]
    }
  }
}

{
  "servers": {
    "daisyui": {
      "command": "/home/username/fastmcp/venv/bin/python",
      "args": ["/home/username/fastmcp/mcp_server.py"]
    }
  }
}

📁 Project Structure

fastmcp/
├── 🐍 mcp_server.py          # The MCP server
├── 🔄 update_components.py   # Script to fetch/update component docs
├── 📋 requirements.txt       # Dependencies (just fastmcp)
├── 🐳 Dockerfile             # Docker image definition
├── 🐳 docker-compose.yml     # Docker Compose configuration
└── 📂 components/            # Markdown files for each component
    ├── button.md
    ├── card.md
    ├── modal.md
    ├── table.md
    └── ... (60+ components)

🤝 Contributing

Contributions are welcome! Feel free to:

• 🐛 Report bugs
• 💡 Suggest new features
• 📝 Improve documentation
• 🔧 Submit pull requests

📄 License