UML MCP Server

@antoinebou12

リポジトリ

基本情報

カテゴリ

その他

ライセンス

MIT license

トランスポート

stdio

作者

antoinebou12

投稿者

Antoine Boucher

UML MCP Server について

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

#uml-mcp#diagram-generation#mcp-interface

UML MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "uml-mcp": {
      "transport": "http",
      "url": "https://uml-mcp.vercel.app/mcp"
    },
    "sequential-thinking": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-sequential-thinking"
      ]
    }
  }
}

UML MCP Server のツール

List supported diagram types with Kroki backend, description, and formats (same data as uml://types resource). Use when the client cannot read resources.

Generate multiple diagrams in one call. Each item is like generate_uml (diagram_type, code, output_format?, theme?, scale?). Optional shared output_dir for all items. Returns a list of per-index results or errors.

Generate any UML or diagram by type (class, sequence, mermaid, d2, etc.)

Validate diagram type, format, code length, and basic syntax locally before render (no Kroki call). Returns errors and suggestions.

概要

What is UML-MCP?

UML-MCP is a diagram generation server that implements the Model Context Protocol (MCP), enabling AI assistants and other applications to create UML diagrams, Mermaid, D2, Graphviz, ERD, and more. It connects to rendering services like PlantUML and Kroki, making diagram creation seamless from supported clients.

How to use UML-MCP?

Install Python 3.10+, clone the repository, and run python mcp_server.py. Configure the server in Claude Desktop or Cursor via mcpServers JSON pointing to the script. Use the provided tools (e.g., generate_uml, generate_class_diagram) with parameters like diagram_type, code, and output_dir. Environment variables such as MCP_OUTPUT_DIR, KROKI_SERVER, and PLANTUML_SERVER control rendering services.

Key features of UML-MCP

Supports UML, Mermaid, D2, Graphviz, ERD, and more diagram types
Seamless MCP integration with AI assistants
Direct playground links for online editing
Multiple output formats: SVG, PNG, PDF, and others
Simple configuration with local or remote rendering servers

Use cases of UML-MCP

Generate UML class, sequence, or activity diagrams from AI chat prompts
Create ERDs and BPMN diagrams for database or process documentation
Automate diagram production for software documentation and reports
Integrate diagram generation into IDEs like Cursor or Claude Desktop

よくある質問

What diagram types does UML-MCP support?

UML-MCP supports UML (Class, Sequence, Activity, Use Case, State, Component, Deployment, Object), Mermaid, D2, Graphviz, ERD, BlockDiag, BPMN, and C4 with PlantUML.

What are the runtime requirements?

Python 3.10 or higher and pip. Optionally, Docker for local PlantUML or Kroki servers.

How can I use local rendering servers?

Set `USE_LOCAL_PLANTUML=true` and `PLANTUML_SERVER=http://localhost:8080` (or `USE_LOCAL_KROKI=true` and `KROKI_SERVER=http://localhost:8000`), then start the corresponding Docker containers.

What output formats are available?

SVG, PNG, PDF, and other formats depending on the diagram type and rendering engine.

How do I integrate UML-MCP with Cursor?

Run `python mcp/install_to_cursor.py` or manually add the server configuration in Cursor settings under `mcpServers` with the command and arguments pointing to `mcp_server.py`.

「その他」の他のコンテンツ

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

Volley.sh

Volley

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi