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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.