MCP Images

🚀 MCP Server - Images

An MCP (Model Context Protocol) server that provides tools for retrieving and processing images from URLs, local file paths, and numpy arrays. This server supports multiple image formats and can encode images as Base64 strings.

✨ Features

• Supports a variety of common image formats (e.g., JPEG, PNG, etc.).
• Provides the ability to load images from URLs.
• Supports loading from local file paths.
• Automatically handles image scaling and format conversion.
• Returns Base64-encoded strings.

📦 Installation

Prerequisites

1. Install Python 3.8 or higher.
2. Ensure the dependencies Pillow and numpy are installed.
   • You can install them using the following command:

     pip install Pillow numpy
     

Steps

1. Clone this repository to your local machine:

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

2. Run the server:

   python server.py
   

🚀 Quick Start

Direct Run

1. Make sure all dependencies are installed.
2. Start the server:

   python server.py --port 5000
   

3. Open your browser and visit http://localhost:5000.

Configure as a Windows or Linux Service (Optional)

1. Create a startup script (e.g., start_server.sh):

   #!/bin/bash
   python server.py --port 5000
   

2. Add execution permissions:

   chmod +x start_server.sh
   

3. Start the service:

   ./start_server.sh
   

💻 Usage Examples

Image Processing Tools

• process_image: Process a single image.
  • Parameters
    • image_path: Image path (supports URLs and local file paths).
    • output_format: Output format, default is PNG.
    • max_size: Maximum size, default is 800x600.

🔧 Debugging

1. Check if all dependencies are installed correctly.
2. Ensure the server is started and running properly.
3. For local loading issues, check if the file path is correct and accessible.
4. Check the error messages in the server output.

💪 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🌟 Support Us

If you like this project or have any questions, please consider supporting us: Buy Me a Coffee