Uml MCP

🚀 UML Diagram Generation Server Documentation

This documentation provides a detailed guide on installing, configuring, and using the UML diagram generation server. It also includes information on development, project structure, and contribution guidelines.

📦 Installation Guide

Installing Claude Desktop on MacOS

Path: ~/Library/Application\ 支持/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "uml_diagram_generator": {
      "command": "python",
      "args": [
        "/path/to/uml-mcp/mcp_server.py"
      ]
    }
  }
}

Installing Claude Desktop on Windows

Path: %APPDATA%/Claude/claude_desktop_config.json

⚙️ Configuration Guide

Integrating the UML Diagram Generation Server in Cursor

{
  "mcpServers": {
    "uml_diagram_generator": {
      "command": "python",
      "args": [
        "/path/to/uml-mcp/mcp_server.py"
      ]
    }
  }
}

💻 Usage Examples

Command Line Arguments

usage: mcp_server.py [-h] [--debug] [--host HOST] [--port PORT] [--transport {stdio,http}] [--list-tools]

UML-MCP Graph Generation Server

Options:
  -h, --help            Show this help message and exit
  --debug               Enable debug logging
  --host HOST           Server host (default: 127.0.0.1)
  --port PORT           Server port (default: 8000)
  --transport {stdio,http}
                        Transport protocol (default: stdio)
  --list-tools          List all tools and exit

Environment Variable Configuration

• LOG_LEVEL: Set the log level (DEBUG, INFO, WARNING, ERROR, CRITICAL)
• UML_MCP_OUTPUT_DIR: Directory to store generated chart files
• KROKI_SERVER: Kroki server URL address for chart rendering
• PLANTUML_SERVER: PlantUML server URL address for chart rendering
• LIST_TOOLS: Set to "true" to display the tool list and exit

Example: Generate a Class Diagram

result = tool.call("generate_class_diagram", {
    "code": """
        @startuml
        class User {
          -id: int
          -name: string
          +login(): boolean
        }
        class Order {
          -id: int
          +addItem(item: string): void
        }
        User "1" -- "many" Order
        @enduml
    """,
    "output_dir": "/path/to/output"
})

🛠️ Development Guide

Building and Running

# Clone the repository
git clone https://github.com/your-username/uml-mcp.git
cd uml-mcp

# Install dependencies
pip install -r requirements.txt

# Run the server
python mcp_server.py

Debug Mode

python mcp_server.py --debug

Debug logs will be stored in the logs/ directory.

Test Code Example

result = tool.call("generate_class_diagram", {
    "code": """
        @startuml
        class User {
          -id: int
          -name: string
          +login(): boolean
        }
        class Order {
          -id: int
          +addItem(item: string): void
        }
        User "1" -- "many" Order
        @enduml
    """,
    "output_dir": "/path/to/output"
})

📚 Documentation

Server Function Overview

• Supports multiple chart types such as UML class diagrams and sequence diagrams.
• Provides a RESTful API interface for interaction.
• An extensible plugin system supports custom chart generation logic.

Installing Dependencies

pip install -r requirements.txt

Starting the Server

python mcp_server.py

Debug Information

• Log levels: DEBUG, INFO, WARNING, ERROR, CRITICAL
• Log file: logs/debug.log

Example Code

# Basic Usage
from uml_generator import UMLGenerator

generator = UMLGenerator()
diagram_code = '''
@startuml
class User {
  -id: int
  -name: string
  +login(): boolean
}
@enduml
'''
output_path = "examples/output.png"
generator.generate(diagram_code, output_path)

Advanced Features

• Supports batch processing of multiple charts.
• Provides a progress bar to display the generation status.
• Allows custom output formats (PNG, SVG, PDF).

📁 Project Structure

Directory Explanation

.
├── uml_generator/
│   ├── __init__.py
│   ├── generator.py          # Main generator class
│   ├── plugins/              # Plugin directory
│   └── utils.py             # Utility functions
├── requirements.txt         # Dependency management file
└── mcp_server.py            # Service startup script

Code Structure

generator.py

class UMLGenerator:
    def __init__(self):
        self.plugins = []

    def add_plugin(self, plugin):
        """Add a custom plugin"""
        self.plugins.append(plugin)

    def generate(self, code, output_path):
        """Generate a chart"""
        pass

utils.py

import logging

def setup_logging():
    """Configure the logging system"""
    logging.basicConfig(
        level=logging.DEBUG,
        format='%(asctime)s - %(name)s - %(levelname)s - %(message)s'
    )

📖 Usage Guide

Quick Start

1. Install dependencies: pip install -r requirements.txt
2. Initialize the generator:

from uml_generator import UMLGenerator

generator = UMLGenerator()

3. Generate a chart:

diagram_code = '''
@startuml
class User {
  -id: int
}
@enduml
'''
generator.generate(diagram_code, "output.png")

Advanced Configuration

• Add a custom plugin:

from uml_generator.plugins.example_plugin import ExamplePlugin

generator.add_plugin(ExamplePlugin())

• Set the log level:

import logging

logging.getLogger("uml_generator").setLevel(logging.INFO)

❌ Error Handling

Common Issues

1. Dependency packages not installed: Please check requirements.txt and reinstall.
2. Logs not displaying: Please confirm that the log file permissions and path settings are correct.

Error Message Example

Traceback (most recent call last):
  File "mcp_server.py", line 18, in <module>
    from uml_generator.generator import UMLGenerator
ModuleNotFoundError: No module named 'uml_generator'

🤝 Contribution Guide

Code Submission Guidelines

• Follow the PEP8 coding style.
• Provide detailed commit messages.
• Ensure that unit tests pass.

Collaboration Process

1. Fork the project repository.
2. Create a feature branch.
3. Submit code and push to the remote repository.
4. Submit a Pull Request.