Azure Diagram MCP Server
Enables creation of Azure architecture diagrams from natural language descriptions, generating PNG images automatically.
README
Model Context Protocol (MCP) server for Microsoft Azure Diagrams


This tool lets you create Microsoft Azure architecture diagrams automatically. You write a short description (using GitHub Copilot in Visual Studio Code to generate it), and the server will turn it into a diagram image. It’s perfect for anyone who wants to quickly draw cloud diagrams without dragging shapes around.
What's included
This MCP server seamlessly creates diagrams using the Python diagrams package DSL. This server allows you to generate Microsoft Azure diagrams, sequence diagrams, flow diagrams, and class diagrams using Python code.
What it does
- Turn a short plain-English sentence into a clean Azure architecture diagram (PNG).
- Uses the Python
diagramspackage and Azure icons behind the scenes. - Saves images into the
diagrams/folder in this project.
Features
The Diagrams MCP Server provides the following capabilities:
- Generate Diagrams: Create Azure diagrams using Python code
- Multiple Diagram Types: Support for Azure architecture, sequence diagrams, flow charts, class diagrams, and more
- Customization: Customize diagram appearance, layout, and styling
What you’ll need
- Visual Studio Code installed → Download here
- GitHub Copilot → Enable here
- Python → we’ll install this in the steps below
- GraphViz (a small program that actually draws the diagrams) → Download here Don’t worry — we’ll go step by step!
Setup Steps or use .devcontainer
1. Install Python
Open a terminal (Command Prompt, PowerShell, or VS Code Terminal) and run:
winget install Python.Python.3.10
⚠️ Make sure the Python installation path is added to your system's environment variables so that python works in the terminal.
Typically, the installer does this automatically, but if not, you can follow this guide.
2. Install GraphViz
Download and install from: https://graphviz.org/download/
On Windows: pick the MSI installer.
On Mac: use Homebrew (brew install graphviz).
3. Get the MCP Server
Clone this repository (or download the ZIP and unzip it). Then open it in VS Code.
In the VS Code terminal, run:
pip install -r requirements.txt
4. MCP Configuration
Configure the MCP server in your MCP client configuration (e.g., for Visual Studio Code GitHub Copilot ~/.vscode/mcp.json):
{
"mcpServers": {
"Azure Diagram MCP Server": {
"type": "stdio",
"command": "python",
"args": [
"-m", "azure_diagram_mcp_server.server"
],
"cwd": "PARENT_FOLDER_OF_CLONED_REPO",
}
}
}
or docker after a successful docker build -t azure-diagram-mcp-server .:
{
"mcpServers": {
"Azure Diagram MCP Server": {
"command": "docker",
"args": [
"run",
"--rm",
"--interactive",
"--env",
"azure-diagram-mcp-server:latest"
],
"disabled": false,
"autoApprove": []
}
}
}
That’s it! 🎉 You now have everything installed.
Using it with GitHub Copilot
-
Open up
VS Code GitHub Copilot Agent Mode -
Type the following into the chat:
Generate an Azure Architecture Diagram with an Azure Function connected to a SQL Database through a Load Balancer -
GitHub Copilot will want to execute the MCP Function
generate_diagram. Please click onAllowto continue. -
A PNG image will be created in the
diagramsfolder. Open it and admire your Azure diagram! 🚀
Example prompt ideas
Generate an Azure Architecture Diagram with an Azure Function connected to a SQL Database through a Load BalancerGenerate an Azure Architecture Diagram for a simple web app: Azure Front Door to App Service with Azure SQLGenerate an Azure Architecture Diagram to show an AKS cluster with Application Gateway and Azure SQL
Example Diagram
Generate an Azure Architecture Diagram to show an AKS cluster with Application Gateway and Azure SQL


Troubleshooting
- No image appears? Make sure GraphViz is installed (see step 2).
- Copilot doesn’t run? Make sure the GitHub Copilot extension is enabled and that you allowed it to run MCP functions. Check the MCP server too.
- Still stuck? Restart VS Code and try again.
✨ That’s it! You can now create Azure diagrams in minutes with just a few words and GitHub Copilot.
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。