mclabs.gcp-diagram-mcp-server 1.0.5

An MCP server that seamlessly creates GCP diagrams using the Python diagrams package DSL

GCP Diagram MCP Server

Model Context Protocol (MCP) server for GCP Diagrams

This MCP server that seamlessly creates diagrams using the Python diagrams package DSL. This server allows you to generate GCP diagrams, sequence diagrams, flow diagrams, and class diagrams using Python code.

Prerequisites

1. Install uv from Astral or the GitHub README
2. Install Python using uv python install 3.10
3. Install GraphViz https://www.graphviz.org/

Installation

Cursor	VS Code

Configure the MCP server in your MCP client configuration (e.g., for Google AI Studio CLI, edit your MCP client config):

{
  "mcpServers": {
    "mclabs.gcp-diagram-mcp-server": {
      "command": "uvx",
      "args": ["mclabs.gcp-diagram-mcp-server"],
      "env": {
        "FASTMCP_LOG_LEVEL": "ERROR"
      },
      "autoApprove": [],
      "disabled": false
    }
  }
}

or docker after a successful docker build -t mclabs/gcp-diagram-mcp-server .:

  {
    "mcpServers": {
      "mclabs.gcp-diagram-mcp-server": {
        "command": "docker",
        "args": [
          "run",
          "--rm",
          "--interactive",
          "--env",
          "FASTMCP_LOG_LEVEL=ERROR",
          "mclabs/gcp-diagram-mcp-server:latest"
        ],
        "env": {},
        "disabled": false,
        "autoApprove": []
      }
    }
  }

Features

The Diagrams MCP Server provides the following capabilities:

1. Generate Diagrams: Create professional diagrams using Python code
2. Multiple Diagram Types: Support for GCP architecture, sequence diagrams, flow charts, class diagrams, and more
3. Customization: Customize diagram appearance, layout, and styling
4. Security: Code scanning to ensure secure diagram generation

Quick Example

from diagrams import Diagram
from diagrams.gcp.compute import Functions
from diagrams.gcp.database import Firestore
from diagrams.gcp.network import LoadBalancing

with Diagram("Serverless Application", show=False):
    lb = LoadBalancing("Load Balancer")
    function = Functions("Cloud Function")
    database = Firestore("Firestore")

    lb >> function >> database

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):

pytest -xvs tests/

To run with coverage:

pytest --cov=mclabs.gcp_diagram_mcp_server --cov-report=term-missing tests/

For more information about the tests, see the tests README.

Development Dependencies

To set up the development environment, install the development dependencies:

uv pip install -e ".[dev]"

This will install the required dependencies for development, including pytest, pytest-asyncio, and pytest-cov.

Acknowledgments

This project is based on the excellent work from the AWS Labs MCP project. We are grateful to the AWS Labs team for creating the original AWS Diagram MCP Server, which served as the foundation for this GCP version.

Original Project

• Original Repository: awslabs/mcp
• Original Package: awslabs.aws-diagram-mcp-server
• License: Apache License 2.0

Special thanks to the AWS Labs team and all contributors to the original project for their innovative work in creating MCP servers for cloud architecture diagrams.