Diagram AI Generator
AI-powered architecture diagram generator with MCP server integration. Create professional cloud diagrams (AWS, Azure, GCP, K8s) with real provider icons. Works seamlessly with Claude Desktop.
What is Diagram AI Generator?
Diagram AI Generator is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ai-powered architecture diagram generator with mcp server integration. create professional cloud diagrams (aws, azure, gcp, k8s) with real provider icons. works seamlessly with claude desktop.
AI-powered architecture diagram generator with MCP server integration. Create professional cloud diagrams (AWS, Azure, GCP, K8s) with real provider icons. Works seamlessly with Claude Desktop.
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- AI-powered architecture diagram generator with MCP server in
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx diagram-ai-generatorConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Diagram AI Generator
Diagram AI Generator is a Python-based MCP server that generates professional cloud architecture diagrams for AWS, Azure, GCP, Kubernetes, and 14+ other providers using real provider icons. It integrates with Claude Desktop and guides users through a structured three-step workflow to discover providers, select component categories, get exact node names, and generate diagrams as image files.
Prerequisites
- Python 3.10 or newer installed
- Graphviz installed (brew install graphviz on macOS, or https://graphviz.org/download/ on Windows/Linux)
- pip for installing the Python package
- Claude Desktop or another MCP-compatible client
Install Graphviz
Graphviz is a required system dependency for rendering diagram files. Install it before the Python package.
# macOS:
brew install graphviz
# Ubuntu/Debian:
sudo apt-get install graphviz
# Windows (winget):
winget install graphvizInstall the diagram-ai-generator package
Install the package from PyPI using pip or your system Python.
pip install diagram-ai-generator
# macOS (if pip maps to Python 2):
/usr/local/bin/python3 -m pip install diagram-ai-generatorConfigure Claude Desktop
Edit your Claude Desktop config file to register the MCP server. Use python3 to run the modular server module.
{
"mcpServers": {
"diagram-ai-generator": {
"command": "python3",
"args": ["-m", "src.application.mcp.server_modular"]
}
}
}Set a custom output directory (optional)
By default, diagrams are saved to ./generated_diagrams/ relative to the server working directory. Override this with the DIAGRAM_OUTPUT_DIR environment variable.
{
"mcpServers": {
"diagram-ai-generator": {
"command": "python3",
"args": ["-m", "src.application.mcp.server_modular"],
"env": {
"DIAGRAM_OUTPUT_DIR": "/Users/yourname/diagrams"
}
}
}
}Restart Claude Desktop and verify
Close and reopen Claude Desktop. Ask Claude to list available diagram providers to confirm the server is connected.
# Ask Claude:
# "List all available cloud providers for diagram generation"Generate your first diagram
Use the three-step workflow: list providers, get categories, get nodes, then create the diagram. Or describe what you want and let Claude orchestrate the steps.
# Ask Claude:
# "Create an AWS serverless architecture diagram with API Gateway, Lambda, and DynamoDB"
# "Generate a Kubernetes cluster diagram showing a web app with ingress, deployment, and service"
# "Make a multi-cloud diagram combining AWS Lambda and Azure Functions"Diagram AI Generator Examples
Client configuration
Claude Desktop claude_desktop_config.json with diagram-ai-generator and a custom output directory.
{
"mcpServers": {
"diagram-ai-generator": {
"command": "python3",
"args": ["-m", "src.application.mcp.server_modular"],
"env": {
"DIAGRAM_OUTPUT_DIR": "/Users/yourname/Desktop/diagrams"
}
}
}
}Prompts to try
Architecture diagram generation prompts for Claude with the diagram-ai-generator server connected.
- "List all available cloud providers for diagram generation"
- "Create an AWS three-tier web architecture with ALB, EC2 Auto Scaling, and RDS"
- "Generate a GCP data pipeline diagram with Pub/Sub, Dataflow, and BigQuery"
- "Show me the available Azure networking components I can use in a diagram"
- "Create a multi-cloud diagram with AWS API Gateway fronting Azure Functions"Troubleshooting Diagram AI Generator
Diagram generation fails with 'graphviz executable not found'
Graphviz must be installed as a system binary, not just as a Python package. On macOS run 'brew install graphviz', on Ubuntu run 'sudo apt-get install graphviz'. After installing, restart your terminal and Claude Desktop to ensure the PATH is updated.
Module 'src.application.mcp.server_modular' not found when starting the server
The server must be run from the repository root directory where the 'src' folder exists. If you installed via pip, the module paths may differ. Try running 'python3 -m diagram_ai_generator.mcp.server' or check the installed package structure with 'pip show diagram-ai-generator'.
Diagrams are generated but cannot be found on disk
Check the DIAGRAM_OUTPUT_DIR environment variable setting. If not set, diagrams are saved to ./generated_diagrams/ relative to where the server process was started — which may be an unexpected directory. Set DIAGRAM_OUTPUT_DIR to an absolute path in your MCP config env section.
Frequently Asked Questions about Diagram AI Generator
What is Diagram AI Generator?
Diagram AI Generator is a Model Context Protocol (MCP) server that ai-powered architecture diagram generator with mcp server integration. create professional cloud diagrams (aws, azure, gcp, k8s) with real provider icons. works seamlessly with claude desktop. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Diagram AI Generator?
Follow the installation instructions on the Diagram AI Generator GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Diagram AI Generator?
Diagram AI Generator works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Diagram AI Generator free to use?
Yes, Diagram AI Generator is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Diagram AI Generator Alternatives — Similar Developer Tools Servers
Looking for alternatives to Diagram AI Generator? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Diagram AI Generator 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 Diagram AI Generator?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.