Uml MCP Server
U

Uml MCP Server

UML-MCP-Server is a UML diagram generation tool based on the MCP protocol. It supports generating multiple types of UML diagrams through natural language descriptions or by directly writing PlantUML code, and can be integrated into clients such as Cursor that support MCP.
2.5 points
6.3K

What is UML-MCP-Server?

UML-MCP-Server is an intelligent UML diagram generation tool that can create professional UML diagrams through simple natural language descriptions or by directly writing PlantUML code. It supports multiple UML diagram types and can be used as an MCP server integrated with clients (such as Claude) that support this protocol.

How to use UML-MCP-Server?

You can use it in three ways: 1) Call it as a Python library. 2) Configure it in the Cursor IDE. 3) Directly call it through clients (such as Claude) that support the MCP protocol. No matter which way you choose, you can easily generate UML diagrams and get shareable links and local files.

Applicable scenarios

It is suitable for scenarios that require visual expression of system structure and processes, such as software development design stages, system architecture documentation writing, teaching demonstrations, and technical solution exchanges. It is especially suitable for agile development teams that need to quickly generate and iterate UML diagrams.

Main features

Support for multiple UML diagram types
Supports mainstream UML diagram types such as class diagrams, sequence diagrams, activity diagrams, use case diagrams, state diagrams, component diagrams, deployment diagrams, and object diagrams
Natural language generation
Corresponding UML diagrams can be generated through simple natural language descriptions without mastering professional UML syntax
PlantUML integration
Supports generating diagrams directly using PlantUML code, providing flexible control for professional users
MCP protocol support
Can be seamlessly integrated as an MCP server with clients (such as Claude) that support this protocol
Local save
Automatically saves the generated diagrams to a specified local directory for easy management and version control
Advantages
No professional UML knowledge is required, and diagrams can be generated through natural language
Supports multiple UML diagram types to meet different scenario requirements
Provides two save methods: online links and local files
Can be seamlessly integrated with AI assistants such as Claude
Flexible configuration options allow customizing the output directory
Limitations
Depends on the PlantUML online service and requires an internet connection
Complex diagrams may require precise natural language descriptions
Correct file permissions need to be configured for local saving
Advanced customization functions require knowledge of PlantUML syntax

How to use

Installation
It can be automatically installed through Smithery or manually installed by cloning the repository
Configure Cursor IDE
Modify the Cursor configuration file and add the MCP server configuration
Generate UML diagrams
Use the UML tool in the Cursor chat window or directly input natural language descriptions
View results
Get the PlantUML code, online link, and local file path

Usage examples

Generate a class diagram
Create a class diagram describing the user and order systems
Generate a sequence diagram
Create a sequence diagram for the user login process
Generate an activity diagram
Create an activity diagram for the order processing flow

Frequently Asked Questions

How to solve the problem of being unable to generate UML diagrams?
What if the pictures are not saved locally?
How to generate more complex UML diagrams?
What if the MCP server fails to start?

Related resources

PlantUML official documentation
PlantUML syntax reference documentation
GitHub repository
Project source code repository
MCP protocol introduction
Official introduction to the Model Context Protocol
Installation tutorial video
Video tutorial on installing and configuring UML-MCP-Server

Installation

Copy the following command to your Client for configuration
{
    "mcpServers": {
        "UML-MCP-Server": {
            "command": "uv",
            "args": [
                "--directory",
                "/Users/yourpath/UML-MCP-Server",
                "run",
                "uml_mcp_server.py"
            ],
            "output_dir": "/Users/yourpath/uml-output"
        }
    }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

R
Rsdoctor
Rsdoctor is a build analysis tool specifically designed for the Rspack ecosystem, fully compatible with webpack. It provides visual build analysis, multi - dimensional performance diagnosis, and intelligent optimization suggestions to help developers improve build efficiency and engineering quality.
TypeScript
8.7K
5 points
N
Next Devtools MCP
The Next.js development tools MCP server provides Next.js development tools and utilities for AI programming assistants such as Claude and Cursor, including runtime diagnostics, development automation, and document access functions.
TypeScript
8.2K
5 points
T
Testkube
Testkube is a test orchestration and execution framework for cloud-native applications, providing a unified platform to define, run, and analyze tests. It supports existing testing tools and Kubernetes infrastructure.
Go
5.1K
5 points
M
MCP Windbg
An MCP server that integrates AI models with WinDbg/CDB for analyzing Windows crash dump files and remote debugging, supporting natural language interaction to execute debugging commands.
Python
9.5K
5 points
R
Runno
Runno is a collection of JavaScript toolkits for securely running code in multiple programming languages in environments such as browsers and Node.js. It achieves sandboxed execution through WebAssembly and WASI, supports languages such as Python, Ruby, JavaScript, SQLite, C/C++, and provides integration methods such as web components and MCP servers.
TypeScript
7.4K
5 points
N
Netdata
Netdata is an open-source real-time infrastructure monitoring platform that provides second-level metric collection, visualization, machine learning-driven anomaly detection, and automated alerts. It can achieve full-stack monitoring without complex configuration.
Go
8.6K
5 points
M
MCP Server
The Mapbox MCP Server is a model context protocol server implemented in Node.js, providing AI applications with access to Mapbox geospatial APIs, including functions such as geocoding, point - of - interest search, route planning, isochrone analysis, and static map generation.
TypeScript
6.7K
4 points
U
Uniprof
Uniprof is a tool that simplifies CPU performance analysis. It supports multiple programming languages and runtimes, does not require code modification or additional dependencies, and can perform one-click performance profiling and hotspot analysis through Docker containers or the host mode.
TypeScript
7.2K
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
31.0K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
18.9K
4.5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
21.6K
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
61.9K
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
26.8K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
57.3K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
18.8K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
41.1K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase