Azure Diagram
MCP server that turns natural-language prompts into Microsoft Azure architecture diagrams (PNG) using Python Diagrams + Graphviz.
What is Azure Diagram?
Azure Diagram is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server that turns natural-language prompts into microsoft azure architecture diagrams (png) using python diagrams + graphviz.
MCP server that turns natural-language prompts into Microsoft Azure architecture diagrams (PNG) using Python Diagrams + Graphviz.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP server that turns natural-language prompts into Microsof
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx azure-diagramConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Azure Diagram
The Azure Diagram MCP Server converts natural-language architecture descriptions into Microsoft Azure infrastructure diagrams rendered as PNG files, using the Python diagrams library and Graphviz for rendering. It exposes a generate_diagram tool that interprets plain-English prompts like 'an Azure Function connected to SQL Database through a Load Balancer' and produces professional architecture visuals saved to the local diagrams/ folder. DevOps engineers, cloud architects, and solution designers use it to rapidly sketch and document Azure topologies without manually placing icons in drawing tools.
Prerequisites
- Python 3.10+ installed on your system
- Graphviz installed and available on system PATH (required for diagram rendering)
- The Python diagrams package and project dependencies installed via pip
- Visual Studio Code with GitHub Copilot (primary tested client) or another MCP-compatible client
Install Graphviz on your system
Graphviz must be installed at the OS level before the Python diagrams package can render PNGs. Install it using your system package manager.
# macOS
brew install graphviz
# Ubuntu/Debian
apt-get install graphviz
# Windows (via Chocolatey)
choco install graphvizClone the repository and install Python dependencies
Clone the azure-diagram-mcp repository and install all required Python packages from requirements.txt.
git clone https://github.com/dminkovski/azure-diagram-mcp.git
cd azure-diagram-mcp
pip install -r requirements.txtConfigure your MCP client to run the server
Add the server to your MCP client configuration. Point the command to the Python executable and the server's main script. Update the path to match where you cloned the repository.
{
"mcpServers": {
"azure-diagram": {
"command": "python",
"args": ["/path/to/azure-diagram-mcp/server.py"]
}
}
}Create the output directory
The server saves generated diagrams to a diagrams/ folder relative to the working directory. Create it if it does not exist.
mkdir -p /path/to/azure-diagram-mcp/diagramsRestart your MCP client and generate your first diagram
Restart your client. Describe an Azure architecture in plain English and the generate_diagram tool will render a PNG. The diagram is saved to the diagrams/ folder and the path is returned.
Azure Diagram Examples
Client configuration
MCP configuration for running the Azure Diagram server via Python, pointing to the cloned repository's server script.
{
"mcpServers": {
"azure-diagram": {
"command": "python",
"args": ["/Users/me/projects/azure-diagram-mcp/server.py"]
}
}
}Prompts to try
Natural-language architecture descriptions that the generate_diagram tool converts into Azure architecture PNGs.
- "Generate an Azure architecture diagram with an Azure Function connected to a SQL Database through a Load Balancer"
- "Create a diagram showing an API Gateway routing traffic to three App Services backed by a Redis Cache"
- "Draw an Azure data pipeline: Event Hub → Stream Analytics → Azure Data Lake → Power BI"
- "Diagram a hub-and-spoke Azure Virtual Network topology with a firewall in the hub"Troubleshooting Azure Diagram
Error: 'dot' executable not found or Graphviz not on PATH
Graphviz must be installed at the OS level and its 'dot' binary must be on your system PATH. After installing via brew/apt/choco, run 'dot -V' to confirm it's accessible. On macOS, you may need to add /usr/local/bin or /opt/homebrew/bin to your PATH.
generate_diagram fails with 'module diagrams not found'
The Python diagrams package must be installed in the same Python environment the server is running in. Run 'pip install diagrams' in the correct environment, or use a virtual environment: 'python -m venv venv && source venv/bin/activate && pip install -r requirements.txt'.
Diagram is generated but the PNG appears blank or contains only text
The Azure icon set requires specific versions of the diagrams package. Ensure you're installing from requirements.txt (not just 'pip install diagrams') to get the exact version tested with the server. Also verify Graphviz is version 2.40 or newer.
Frequently Asked Questions about Azure Diagram
What is Azure Diagram?
Azure Diagram is a Model Context Protocol (MCP) server that mcp server that turns natural-language prompts into microsoft azure architecture diagrams (png) using python diagrams + graphviz. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Azure Diagram?
Follow the installation instructions on the Azure Diagram GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Azure Diagram?
Azure Diagram works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Azure Diagram free to use?
Yes, Azure Diagram is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Azure Diagram Alternatives — Similar Cloud Services Servers
Looking for alternatives to Azure Diagram? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Azure Diagram in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Azure Diagram?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.