UML

super cool MCP for making UMLs in python

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "cool-coder174-uml-mcp": {
      "command": "python",
      "args": [
        "-m",
        "mcp_server.server"
      ]
    }
  }
}

You run an MCP server that exposes a dedicated tool to generate UML diagrams from requests. This Python-based service uses Gemini-backed PlantUML generation and a gRPC interface, making it easy to produce UML Class and Sequence diagrams from client code or automation pipelines.

How to use

Spawn the MCP server locally and then use your MCP client to request UML diagrams. Start the MCP server so other processes can send generate_uml requests, and integrate it into your automation or editor workflows. The server provides a straightforward tool named generate_uml that you can invoke from your MCP client to obtain UML diagram representations.

How to install

Prerequisites you need on your machine before proceeding:

Python 3.8+ (recommended) and a working Python environment
Python package manager you use to install dependencies (pip)

Follow these steps to set up and run the MCP server locally:

python -m venv .venv
source .venv/bin/activate
`

pip install -r requirements.txt

Create a Gemini API key file in the project root so the service can authenticate with Gemini. Place your Gemini API key on the first line of a file named key.txt.

echo YOUR_GEMINI_API_KEY > key.txt

Additional notes

No further setup is required for the MCP server beyond creating the key file and installing dependencies. You can then start the MCP server as described in the next section.

Available tools

generate_uml

MCP tool exposed by the UML MCP server to generate UML diagrams from requests.