Model Context Protocol (MCP) server for Multi-Cloud Infrastructure Diagrams
This MCP server seamlessly creates diagrams using the Python diagrams package DSL. Generate professional infrastructure diagrams for (AWS, GCP, Azure), Kubernetes, on-premises, hybrid, and multi-cloud architectures using natural language with Claude Desktop or other MCP clients.
An MCP server that seamlessly creates infrastructure diagrams for AWS, Azure, GCP, Kubernetes and more
Sterne
148
Tools
—
Uptime
—
any cloud provider
Note: This is a derivative work based on awslabs/aws-diagram-mcp-server, extended with multi-cloud provider support and enhanced features.
Prerequisites
Install GraphVizwith development headers - Required for diagram generation and .drawio export
Helm is required for full template rendering with the parse_helm_chart tool. Without Helm, the parser will use a fallback mode with limited template support.
Configure the MCP server in your MCP client. The CFLAGS and LDFLAGS (or INCLUDE and LIB on Windows) environment variables are needed for the initial build of pygraphviz.
Claude Desktop / Cursor on macOS (~/Library/Application Support/Claude/claude_desktop_config.json or ~/.cursor/mcp.json):
✅ Icon Corrections: Fixed 28+ incorrect class names in examples
Code Examples
Below are Python code examples showing the diagrams package syntax. When using with Claude Desktop, you can simply describe what you want in natural language!
AWS Serverless Application
from diagrams import Diagram
from diagrams.aws.compute import Lambda
from diagrams.aws.database import Dynamodb
from diagrams.aws.network import APIGateway
with Diagram("Serverless Application", show=False):
api = APIGateway("API Gateway")
function = Lambda("Function")
database = Dynamodb("DynamoDB")
api >> function >> database
GCP Microservices
from diagrams import Diagram, Cluster
from diagrams.gcp.compute import CloudRun
from diagrams.gcp.network import LoadBalancing
from diagrams.gcp.database import SQL
with Diagram("GCP Microservices", show=False):
lb = LoadBalancing("load balancer")
with Cluster("Services"):
services = [CloudRun("api"), CloudRun("worker")]
db = SQL("database")
lb >> services >> db
Azure Web App
from diagrams import Diagram
from diagrams.azure.web import AppService
from diagrams.azure.database import SQLServer
from diagrams.azure.storage import BlobStorage
with Diagram("Azure Web App", show=False):
AppService("web") >> SQLServer("db") >> BlobStorage("storage")
Multi-Cloud Architecture
from diagrams import Diagram, Cluster
from diagrams.aws.compute import EC2
from diagrams.gcp.compute import CloudRun
from diagrams.azure.web import AppService
with Diagram("Multi-Cloud Setup", show=False):
with Cluster("AWS"):
aws = EC2("primary")
with Cluster("GCP"):
gcp = CloudRun("backup")
with Cluster("Azure"):
azure = AppService("cdn")
aws >> [gcp, azure]
Example Diagrams Gallery
Below are complete architecture diagram examples generated using this MCP server. These demonstrate real-world patterns across different cloud providers and deployment scenarios.
AWS Serverless Architecture
A production-ready serverless architecture using AWS services.
Architecture Components:
Users connecting via HTTPS
API Gateway as the entry point
Multiple Lambda functions for compute
DynamoDB for NoSQL database storage
GCP Serverless Architecture
A serverless architecture on Google Cloud Platform with managed services.
Architecture Components:
Users connecting via HTTPS
Load Balancer for traffic distribution
Cloud Functions for serverless compute
Firestore for document database
Azure Serverless Architecture
A serverless architecture on Microsoft Azure featuring fully managed services.
Architecture Components:
Users connecting via HTTPS
Application Gateway for routing and load balancing
Function Apps for serverless execution
Cosmos DB for globally distributed database
Kubernetes Architecture
A containerized application deployment on Kubernetes with full storage support.
Architecture Components:
Ingress for external access and routing
Service for internal load balancing
Multiple Pods running containerized applications
Persistent Volumes and Claims for stateful storage
Multi-Cloud Architecture
A distributed architecture spanning AWS, GCP, and Azure with global DNS routing for high availability.
Architecture Components:
Global DNS (Route53) for intelligent traffic routing
Azure Region: Load Balancer → Function Apps → Cosmos DB
Hybrid Cloud Architecture
An enterprise hybrid cloud setup connecting on-premises infrastructure to AWS cloud.
Architecture Components:
On-premises application server and PostgreSQL database
VPN Gateway for secure encrypted connectivity
AWS VPC with EC2 instances
RDS for database replication and disaster recovery
S3 for backup and archival storage
GCP Foundation Organization Layer (from Terraform)
A comprehensive GCP organization-level infrastructure parsed from the terraform-example-foundation using the parse_terraform tool.
Architecture Components:
Organization-level resources (VPC Service Controls, Resource Tags, Org Policies)
Parse Helm charts with full helm template rendering or fallback mode when Helm CLI is unavailable.
Note: For best results, install Helm. Without Helm, the parser uses a fallback mode with limited Go template support.
Parse the Helm chart at ./charts/my-app/ with values from values-prod.yaml
Features:
Full Helm template rendering (requires Helm CLI)
Fallback mode for basic parsing without Helm
Custom values file and inline values support
Release name and namespace configuration
parse_terraform
Parse Terraform HCL configurations to extract resources, data sources, modules, and relationships.
Parse the Terraform configuration in ./terraform/ and visualize the infrastructure
Detects:
Resources from AWS, GCP, Azure, and Kubernetes providers
Data sources and module references
Explicit depends_on relationships
Implicit references between resources
Development
Testing
The project includes a comprehensive test suite to ensure the functionality of the MCP server. The tests are organized by module and cover all aspects of the server's functionality.
To run the tests, use the provided script:
./run_tests.sh
This script will automatically install pytest and its dependencies if they're not already installed.
Or run pytest directly (if you have pytest installed):
Noch keine Tool-Liste. Remote-Server erhalten eine nach dem ersten Health-Check.
FAQ
Fragen
Wie installiere ich Diagram?
Kopieren Sie auf dieser Seite die stdio-Konfiguration für Cursor, Claude Desktop, Claude Code oder VS Code. Sie nutzt die Installation des Herausgebers, keinen PlugMCP-Proxy.
Benötigt Diagram einen API-Schlüssel?
In diesem Eintrag ist keine erforderliche Umgebungsvariable aufgeführt.
Welchen Transport verwendet Diagram?
Diagram läuft lokal über stdio.
Wann wurde Diagram zuletzt geprüft?
Zuletzt geprüft: 2026-10-28. An MCP server that seamlessly creates infrastructure diagrams for AWS, Azure, GCP, Kubernetes and more