MCP Panel

AI-powered CAD design copilot for acoustic products (splitter silencers and stratified acoustic panels). Built with FastAPI, Gemini, and MCP tools.

Prerequisites

• Docker and Docker Compose
• A Gemini API key

Setup

1. Clone the repo

git clone <repo-url>
cd Task

2. Create the .env file

cp .env.example .env   # or create it manually

Add your key:

GEMINI_API_KEY=your_key_here

3. Create the data directory

mkdir data

This is where the SQLite database (data/projects.db) will be stored. It is mounted into the container so data persists across restarts.

4. Build and run

docker compose up --build

The app will be available at http://localhost:8000.

Running without Docker

python -m venv env
source env/bin/activate      # Windows: env\Scripts\activate
pip install -r requirements.txt
uvicorn app:app --reload

Project structure

app.py            FastAPI backend + Gemini agent loop
mcp_server.py     MCP tool definitions
engine.py         Silencer drawing engine
engine_panel.py   Panel drawing engine
project_store.py  SQLite-backed project persistence
data/             Mounted volume — contains projects.db
output/           Generated drawings (Docker named volume)
static/           Frontend assets

API

Method	Path	Description
GET	/api/health	Health check
POST	/api/chat	Send a message to the AI copilot
GET	/output/<file>	Retrieve a generated drawing