Diagram
An MCP server that seamlessly creates infrastructure diagrams for AWS, Azure, GCP, Kubernetes and more
What is Diagram?
Diagram is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server that seamlessly creates infrastructure diagrams for aws, azure, gcp, kubernetes and more
An MCP server that seamlessly creates infrastructure diagrams for AWS, Azure, GCP, Kubernetes and more
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- An MCP server that seamlessly creates infrastructure diagram
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx diagramConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Diagram
The Infrastructure Diagram MCP Server is a Python-based tool that lets AI assistants generate architecture diagrams for AWS, Azure, GCP, Kubernetes, and other cloud platforms using the Diagrams-as-code library, which provides over 2000 icons. It exposes three parsing tools that accept Kubernetes manifests, Helm charts, and Terraform HCL files — extracting resources and relationships automatically — and then renders them as PNG diagrams or .drawio files ready for editing in draw.io. Developers and infrastructure engineers use it to visualize cloud architectures, document IaC configurations, and share diagrams without manually maintaining diagram tools.
Prerequisites
- Python 3.8+ with uv or pip package manager
- GraphViz installed with development headers (required by the Python diagrams library)
- Helm CLI installed (optional, required for full Helm chart parsing)
- An MCP-compatible client such as Claude Desktop or Cursor
Install GraphViz with development headers
The Python diagrams library requires GraphViz and its headers. Install the appropriate package for your OS.
# macOS:
brew install graphviz
# Ubuntu/Debian:
sudo apt-get install graphviz graphviz-dev
# Windows:
choco install graphvizSet compiler flags (macOS/Linux)
On macOS and Linux, set CFLAGS and LDFLAGS so that pip can find the GraphViz headers when installing the Python binding.
# macOS example (adjust path from 'brew --prefix graphviz'):
export CFLAGS="-I$(brew --prefix graphviz)/include"
export LDFLAGS="-L$(brew --prefix graphviz)/lib"
# Ubuntu/Debian: usually not needed, headers are in standard pathsInstall Helm (optional)
Install the Helm CLI if you need to parse Helm charts with full template rendering support.
# macOS:
brew install helm
# Linux:
curl https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bashConfigure your MCP client
Add the server entry to your claude_desktop_config.json or equivalent config file. The server is run via uvx using the published package name.
Restart your MCP client and test
Restart Claude Desktop or Cursor and ask it to generate a simple AWS architecture diagram to verify the server is working.
Diagram Examples
Client configuration
Add this block to ~/Library/Application Support/Claude/claude_desktop_config.json. The FASTMCP_LOG_LEVEL is set to ERROR to suppress verbose output; CFLAGS and LDFLAGS are set if GraphViz is in a non-standard location (macOS Homebrew example).
{
"mcpServers": {
"diagram": {
"command": "uvx",
"args": ["infrastructure-diagram-mcp-server"],
"env": {
"FASTMCP_LOG_LEVEL": "ERROR",
"CFLAGS": "-I/opt/homebrew/include",
"LDFLAGS": "-L/opt/homebrew/lib"
}
}
}
}Prompts to try
Infrastructure diagram generation prompts using the server's three parsing tools and free-form diagram creation.
- "Create an AWS serverless architecture diagram with API Gateway, Lambda, and DynamoDB"
- "Generate a GCP data pipeline diagram showing Pub/Sub, Dataflow, and BigQuery"
- "Parse the Kubernetes manifests in ./k8s/ and show me the resources and relationships"
- "Parse the Terraform configuration in ./infrastructure/ and visualize all AWS resources"
- "List all available Azure infrastructure diagram icons"Troubleshooting Diagram
Installation fails with 'graphviz' not found or missing headers
Install GraphViz with development headers before installing the Python package. On macOS: 'brew install graphviz' then set CFLAGS and LDFLAGS to the Homebrew paths. On Ubuntu: 'sudo apt-get install graphviz graphviz-dev'. On Windows, install from graphviz.org and set the INCLUDE and LIB environment variables to the installation path.
Helm chart parsing fails or returns incomplete results
Ensure the Helm CLI is installed and available in PATH ('helm version'). Without Helm, the server falls back to a template-less parsing mode that may miss rendered resource names. Install Helm for full support.
Diagrams are generated but not visible in Claude Desktop
The server writes diagram files to disk. Check the current working directory or a configured output path for .png or .drawio files. Ask Claude where the file was saved, or specify an absolute output path in your request.
Frequently Asked Questions about Diagram
What is Diagram?
Diagram is a Model Context Protocol (MCP) server that mcp server that seamlessly creates infrastructure diagrams for aws, azure, gcp, kubernetes and more It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Diagram?
Follow the installation instructions on the Diagram GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Diagram?
Diagram works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Diagram free to use?
Yes, Diagram is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Diagram Alternatives — Similar Cloud Services Servers
Looking for alternatives to 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 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 Diagram?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.