MCP Server Glm Vision

🚀 MCP Server GLM Vision

An MCP server integrating GLM-4.5V from Z.AI with Claude Code, enabling image analysis and more.

🚀 Quick Start

The MCP Server GLM Vision is a powerful tool that combines GLM-4.5V's vision capabilities with Claude Code. It allows you to analyze images using the advanced features of GLM-4.5V.

✨ Features

• 📷 Image Analysis: Leverage GLM-4.5V's vision capabilities to analyze images.
• 🖥️ Local File Support: Analyze both local image files and image URLs.
• ⚙️ Configurable: Easily set up the server using environment variables.

📦 Installation

Prerequisites

• Python 3.10 or higher
• A GLM API key from Z.AI
• Claude Code installed

Setup

1. Clone or create the project directory:

   cd /path/to/your/project
   

2. Create and activate virtual environment:

   python3 -m venv env
   source env/bin/activate  # On Windows: env\Scripts\activate
   

3. Install dependencies:

   pip install -r requirements.txt
   # or with uv (recommended)
   uv pip install -r requirements.txt
   

4. Set up environment variables:

   cp .env.example .env
   # Edit .env with your GLM API key from Z.AI
   

5. Add the server to Claude Code:

   # Using uv (recommended)
   uv run mcp install -e . --name "GLM Vision Server"
   
   # Or manually add to Claude Desktop configuration:
   claude mcp add-json --scope user glm-vision '{
     "type": "stdio",
     "command": "/path/to/your/project/env/bin/python",
     "args": ["/path/to/your/project/glm-vision.py"],
     "env": {"GLM_API_KEY": "your_api_key_here"}
   }'
   

📚 Documentation

Configuration

Set these environment variables in your .env file:

💻 Usage Examples

Available Tools

glm-vision

Analyze an image file using GLM-4.5V's vision capabilities. Supports both local files and URLs.

Parameters:

• image_path (required): Local file path or URL of the image to analyze
• prompt (required): What to ask about the image
• temperature (optional): Response randomness (0.0 - 1.0, default: 0.7)
• thinking (optional): Enable thinking mode to see model's reasoning process (default: false)
• max_tokens (optional): Maximum tokens in response (max 64K, default: 2048)

Example:

Use the glm-vision tool with:
- image_path: "/path/to/your/image.jpg"
- prompt: "Describe what you see in this image"

Testing

Test the server using the MCP Inspector:

# With uv
uv run python glm-vision.py

# Or with python
python glm-vision.py

🔧 Technical Details

Development

Running Tests

# Install development dependencies
pip install -e ".[dev]"

# Run tests
pytest

# Format code
black .
isort .

# Type checking
mypy glm-vision.py

Troubleshooting

1. API Key Issues: Ensure your GLM_API_KEY is correctly set in the environment.
2. Connection Problems: Check your internet connection and API endpoint.
3. Model Errors: Verify that the model name (GLM_MODEL) is correct and available.

📄 License

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

🤝 Contributing

1. Fork the repository.
2. Create a feature branch.
3. Make your changes.
4. Add tests if applicable.
5. Submit a pull request.

🆘 Support

• For issues related to the GLM API, contact Z.AI support.
• For MCP server issues, please create an issue in the repository.