System Designer MCP Server
Enables AI agents to create, validate, and export UML system models using structured MSON format. Supports generating PlantUML and Mermaid diagrams with direct export to System Designer macOS application.
README
System Designer MCP Server
A Model Context Protocol (MCP) server that provides AI agents with tools to create, validate, and export UML system models. Built with a tool-based approach that empowers LLMs rather than trying to replace their natural language understanding capabilities.
📚 Documentation
- API Reference - Detailed API documentation for all MCP tools
- CLI Guide - Command-line interface usage and examples
- Integration Guide - Platform integration instructions
- Examples - Sample models and use cases
Features
Core Tools
- create_mson_model: Create and validate MSON models from structured data
- validate_mson_model: Validate MSON model consistency and completeness
- generate_uml_diagram: Generate UML diagrams in PlantUML and Mermaid formats
- export_to_system_designer: Export models to System Designer application format
Key Capabilities
- ✅ Tool-Based Architecture: LLMs handle understanding, server handles validation/formatting
- ✅ Type Safety: Comprehensive Zod schema validation for all inputs and outputs
- ✅ Multiple UML Formats: Support for both PlantUML and Mermaid diagram generation
- ✅ System Designer Integration: Direct export to System Designer macOS application
- ✅ Comprehensive Testing: Full test coverage for all tools and functionality
Installation
Prerequisites
- Bun JavaScript runtime
- Node.js compatibility through Bun
Setup
# Clone the repository
git clone <repository-url>
cd system-designer-mcp
# Install dependencies
bun install
# Build the project
bun run build
# Run tests
bun test
Quick Start
Installation
# Clone the repository
git clone <repository-url>
cd system-designer-mcp
# Install dependencies
bun install
# Build the project
bun run build
# Run tests
bun test
Using the MCP Server
- Start the server:
bun run dev
- Example tool usage:
// Create a MSON model
const model = await mcpClient.callTool('create_mson_model', {
name: 'Student Management System',
type: 'class',
description: 'A system for managing students and courses',
entities: [
{
id: 'student',
name: 'Student',
type: 'class',
attributes: [
{ name: 'id', type: 'string', visibility: 'private' },
{ name: 'name', type: 'string', visibility: 'public' },
],
methods: [{ name: 'enroll', returnType: 'void', visibility: 'public' }],
},
],
relationships: [],
});
// Generate UML diagram
const diagram = await mcpClient.callTool('generate_uml_diagram', {
model: model.content[1].json,
format: 'plantuml',
});
// Export to System Designer
const exported = await mcpClient.callTool('export_to_system_designer', {
model: model.content[1].json,
filePath: './student_system.json',
});
CLI Usage
The server includes a CLI tool for testing and model management:
# Test System Designer integration
bun run src/cli.ts test-integration
# Export a test model
bun run src/cli.ts export-model MyModel "Test model description"
# Show configuration
bun run src/cli.ts config
See the CLI Guide for detailed usage instructions.
Example MSON Model Structure
{
"id": "student_system",
"name": "Student Management System",
"type": "class",
"description": "A system for managing students and courses",
"entities": [
{
"id": "student",
"name": "Student",
"type": "class",
"attributes": [
{
"name": "id",
"type": "string",
"visibility": "private"
},
{
"name": "name",
"type": "string",
"visibility": "public"
}
],
"methods": [
{
"name": "enroll",
"parameters": [
{
"name": "course",
"type": "Course"
}
],
"returnType": "void",
"visibility": "public"
}
]
}
],
"relationships": [
{
"id": "enrollment",
"from": "student",
"to": "course",
"type": "association",
"multiplicity": {
"from": "1",
"to": "0..*"
},
"name": "enrolls in"
}
]
}
Tool Reference
For detailed API documentation, see the API Reference.
Available Tools
- create_mson_model - Create and validate MSON models from structured data
- validate_mson_model - Validate MSON model consistency and completeness
- generate_uml_diagram - Generate UML diagrams in PlantUML and Mermaid formats
- export_to_system_designer - Export models to System Designer application format
Platform Integration
The server can be integrated with various platforms:
- Claude Desktop - Native MCP integration
- VS Code - Extension development support
- Web Applications - React/Node.js integration
- CLI Tools - Command-line interface
See the Integration Guide for detailed setup instructions.
Architecture
Tool-Based Approach
This server uses a tool-based architecture that:
- Empowers LLMs: The LLM handles understanding requirements and creating structured data
- Validates Input: Server validates structured input using comprehensive Zod schemas
- Processes Efficiently: Simple, fast processing without complex parsing logic
- Exports Flexibly: Multiple output formats for different use cases
Benefits Over Parser-Based Approaches
- Simplicity: No complex NLP parsing to maintain
- Flexibility: Works with any domain the LLM understands
- Reliability: Fewer moving parts, less error-prone
- Performance: Faster validation and processing
- Extensibility: Easy to add new tools and features
Development
Running Tests
# Run all tests
bun test
# Run tests in watch mode
bun test --watch
Building
# Build for production
bun run build
# Start production server
bun start
Code Structure
src/
├── index.ts # Main MCP server with all tools
├── cli.ts # Command-line interface
└── integration/
└── system-designer.ts # System Designer app integration
test/
└── tool-based.test.ts # Comprehensive test suite
docs/
├── API-REFERENCE.md # Detailed API documentation
├── CLI-GUIDE.md # CLI usage guide
└── INTEGRATION-GUIDE.md # Platform integration guide
examples/
├── banking-system.json # Sample banking system model
├── banking-system-plantuml.puml # PlantUML output example
├── banking-system-mermaid.md # Mermaid output example
└── README.md # Example documentation
Integration with System Designer
The server exports models in a format compatible with the System Designer macOS application:
- File Export: Models are saved as JSON files
- Automatic Integration: Files can be imported directly into System Designer
- Format Compatibility: Uses MSON (Metamodel JavaScript Object Notation) format
Contributing
This project follows a simple contribution model:
- Fork the repository
- Create a feature branch
- Add tests for new functionality
- Ensure all tests pass
- Submit a pull request
License
MIT License - see LICENSE file for details.
Acknowledgments
- Model Context Protocol (MCP) for the tool integration framework
- System Designer for the target macOS application
- Zod for type-safe validation
- Bun for the fast JavaScript runtime
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。