Sponsored by Deepsite.site

UML-MCP: A Diagram Generation Server with MCP Interface

Created By
antoinebou129 months ago
UML-MCP Server is a UML diagram generation tool based on MCP (Model Context Protocol), which can help users generate various types of UML diagrams through natural language description or directly writing PlantUML and Mermaid and Kroki
Content

UML-MCP: A Diagram Generation Server with MCP Interface

License: MIT Python 3.10+ smithery badge

UML-MCP is a powerful diagram generation server that implements the Model Context Protocol (MCP), enabling seamless diagram creation directly from AI assistants and other applications.

🌟 Features

  • Multiple Diagram Types: Support for UML diagrams (Class, Sequence, Activity, etc.), Mermaid, D2, and more
  • MCP Integration: Seamless integration with LLM assistants supporting the Model Context Protocol
  • Playground Links: Direct links to online editors for each diagram type
  • Multiple Output Formats: SVG, PNG, PDF, and other format options
  • Easy Configuration: Works with local and remote diagram rendering services

📋 Supported Diagram Types

UML-MCP supports a wide variety of diagram types:

CategoryDiagram Types
UMLClass, Sequence, Activity, Use Case, State, Component, Deployment, Object
OtherMermaid, D2, Graphviz, ERD, BlockDiag, BPMN, C4 with PlantUML

🚀 Getting Started

Prerequisites

  • Python 3.10 or higher
  • pip (Python package installer)

Installation

  1. Clone the repository:
git clone https://github.com/yourusername/uml-mcp.git
cd uml-mcp
  1. Install the dependencies:
pip install -r requirements.txt
  1. For development environments:
pip install -r requirements-dev.txt

Running the Server

Start the MCP server:

python mcp_server.py

This will start the server using stdio for communication with MCP clients.

🔧 Configuration

Editor Integration

Cursor

To integrate with Cursor:

python mcp/install_to_cursor.py

Or manually configure in Cursor settings:

"mcpServers": {
  "UML-MCP-Server": {
    "command": "python",
    "args": ["/path/to/uml-mcp/mcp_server.py"],
    "output_dir": "/path/to/output"
  }
}

Environment Variables

  • MCP_OUTPUT_DIR - Directory to save generated diagrams (default: ./output)
  • KROKI_SERVER - URL of the Kroki server (default: https://kroki.io)
  • PLANTUML_SERVER - URL of the PlantUML server (default: http://plantuml-server:8080)
  • USE_LOCAL_KROKI - Use local Kroki server (true/false)
  • USE_LOCAL_PLANTUML - Use local PlantUML server (true/false)

📚 Documentation

For detailed documentation, visit the docs directory or our documentation site.

🧩 Architecture

UML-MCP is built with a modular architecture:

  • MCP Server Core: Handles MCP protocol communication
  • Diagram Generators: Supporting different diagram types
  • Tools: Expose diagram generation functionality through MCP
  • Resources: Provide templates and examples for various diagram types

🛠️ Local Development

For local development:

  1. Set up local PlantUML and/or Kroki servers:
# PlantUML
docker run -d -p 8080:8080 plantuml/plantuml-server

# Kroki
docker run -d -p 8000:8000 yuzutech/kroki
  1. Configure environment variables:
export USE_LOCAL_PLANTUML=true
export PLANTUML_SERVER=http://localhost:8080
export USE_LOCAL_KROKI=true  
export KROKI_SERVER=http://localhost:8000

🤝 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.

👏 Acknowledgements

  • PlantUML - UML diagram generation
  • Kroki - Unified diagram generation service
  • Mermaid - Generation of diagrams from text
  • D2 - Modern diagram scripting language

UML-MCP Server

An MCP Server that provides UML diagram generation capabilities through various diagram rendering engines.

Components

Resources

The server provides several resources via the uml:// URI scheme:

  • uml://types: List of available UML diagram types
  • uml://templates: Templates for creating UML diagrams
  • uml://examples: Example UML diagrams for reference
  • uml://formats: Supported output formats for diagrams
  • uml://server-info: Information about the UML-MCP server

Tools

The server implements multiple diagram generation tools:

Universal UML Generator

  • generate_uml: Generate any UML diagram
    • Parameters: diagram_type, code, output_dir

Specific UML Diagram Tools

  • generate_class_diagram: Generate UML class diagrams
    • Parameters: code, output_dir
  • generate_sequence_diagram: Generate UML sequence diagrams
    • Parameters: code, output_dir
  • generate_activity_diagram: Generate UML activity diagrams
    • Parameters: code, output_dir
  • generate_usecase_diagram: Generate UML use case diagrams
    • Parameters: code, output_dir
  • generate_state_diagram: Generate UML state diagrams
    • Parameters: code, output_dir
  • generate_component_diagram: Generate UML component diagrams
    • Parameters: code, output_dir
  • generate_deployment_diagram: Generate UML deployment diagrams
    • Parameters: code, output_dir
  • generate_object_diagram: Generate UML object diagrams
    • Parameters: code, output_dir

Other Diagram Formats

  • generate_mermaid_diagram: Generate diagrams using Mermaid syntax
    • Parameters: code, output_dir
  • generate_d2_diagram: Generate diagrams using D2 syntax
    • Parameters: code, output_dir
  • generate_graphviz_diagram: Generate diagrams using Graphviz DOT syntax
    • Parameters: code, output_dir
  • generate_erd_diagram: Generate Entity-Relationship diagrams
    • Parameters: code, output_dir

Prompts

The server provides prompts to help create UML diagrams:

  • class_diagram: Create a UML class diagram showing classes, attributes, methods, and relationships
  • sequence_diagram: Create a UML sequence diagram showing interactions between objects over time
  • activity_diagram: Create a UML activity diagram showing workflows and business processes

Configuration

Install

Claude Desktop

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json

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

Cursor Integration

The UML-MCP Server can also be integrated with Cursor:

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

Usage

Command Line Arguments

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

UML-MCP Diagram 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 available tools and exit

Environment Variables

  • LOG_LEVEL: Set logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL)
  • UML_MCP_OUTPUT_DIR: Directory to store generated diagram files
  • KROKI_SERVER: Kroki server URL for diagram rendering
  • PLANTUML_SERVER: PlantUML server URL for diagram rendering
  • LIST_TOOLS: Set to "true" to display tools and exit

Example: Generating 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

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

Debugging

For debugging, you can run the server with:

python mcp_server.py --debug

Debug logs will be stored in the logs/ directory.

Running Tests

# Run all tests
pytest

# Run specific tests
pytest tests/test_diagram_tools.py
Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
WindsurfThe new purpose-built IDE to harness magic
Amap Maps高德地图官方 MCP Server
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
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。
Context7Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
Serper MCP ServerA Serper MCP Server
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
Playwright McpPlaywright MCP server
ChatWiseThe second fastest AI chatbot™
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
CursorThe AI Code Editor
DeepChatYour AI Partner on Desktop
Tavily Mcp