🛍️ MCP - MCP for Commerce Platforms - Universal E-commerce Customer Support Assistant

Created By

slavpilusa year ago

MCP for Commerce Platforms

# e-commerce

# customer-support-ai

Overview Content Tools Comments

Content

title: E-commerce Customer Support MCP emoji: 🛍️ colorFrom: blue colorTo: purple sdk: gradio sdk_version: 5.33.0 app_file: app.py pinned: false license: mit tags: ["mcp", "commerce", "customer support" ]

🛍️ MCP - MCP for Commerce Platforms - Universal E-commerce Customer Support Assistant

One Chat, Every Platform - A platform-agnostic customer support assistant that connects to any e-commerce platform through pluggable strategies, using MCP (Model Context Protocol) server and Gradio for the interface.

🎯 Features

📦 Order Management: Track orders, check status, view history
🔄 Returns & Refunds: Initiate returns, process refunds seamlessly
❌ Cancellations: Quick and easy order cancellations
💬 Natural Language: Conversational interface for customer support
🔌 Platform Agnostic: Extensible to any e-commerce platform
🚀 Auto-Deploy: Continuous deployment to Hugging Face Spaces

🏗️ Architecture

The system uses a Strategy Pattern to abstract different e-commerce platforms:

┌─────────────────────────────────────────────────────────┐
│                    Gradio UI Layer                      │
│        (Customer Support Conversational Interface)      │
└─────────────────────────────┬───────────────────────────┘
                              │
┌─────────────────────────────▼───────────────────────────┐
│                    MCP Server Core                      │
│  (Order Management, NLP Processing, Context Engine)     │
└─────────────────────────────┬───────────────────────────┘
                              │
┌─────────────────────────────▼───────────────────────────┐
│              E-commerce Strategy Interface              │
│   (MockData, Shopify, Magento, WooCommerce, etc.)       │
└─────────────────────────────────────────────────────────┘

🚀 Quick Start

Prerequisites

Python 3.10 or higher
Git
Virtual environment tool (venv)

Installation

Clone the repository

git clone https://github.com/slavpilus/mcp.git
cd mcp

Run the setup script (macOS/Linux)

chmod +x scripts/setup_dev.sh
./scripts/setup_dev.sh

Or manually:

# Create virtual environment
python -m venv venv

# Activate virtual environment
# On macOS/Linux:
source venv/bin/activate
# On Windows:
venv\Scripts\activate

# Install dependencies
pip install -r requirements-dev.txt

# Install pre-commit hooks
pre-commit install

Configure environment variables

cp .env.example .env
# Edit .env with your configuration

Run the application
```
python app.py
```
The application will be available at http://localhost:7860

🛠️ Development

Project Structure

mcp/
├── .github/workflows/    # CI/CD pipelines
├── mcp_server/          # Core MCP server implementation
│   ├── strategies/      # E-commerce platform strategies
│   ├── models/          # Data models
│   └── utils/           # Utility functions
├── ui/                  # Gradio UI components
├── tests/               # Test suite
├── app.py               # Main Gradio application
└── requirements.txt     # Python dependencies

Development Workflow

Activate virtual environment

source venv/bin/activate  # macOS/Linux
# or
venv\Scripts\activate     # Windows

Make your changes
- Follow the existing code style
- Add tests for new functionality
- Update documentation as needed

Run code quality checks

# Format code
black .
isort .

# Run linter
ruff check .

# Type checking
mypy mcp_server ui

Run tests

# Run all tests with coverage
pytest

# Run specific test file
pytest tests/unit/test_strategies.py

# Run with verbose output
pytest -v

Commit changes
```
git add .
git commit -m "feat: your feature description"
```
Pre-commit hooks will automatically run code quality checks.

Code Style

This project uses:

Black for code formatting (line length: 88)
isort for import sorting
Ruff for linting
MyPy for type checking

All code must pass these checks before merging.

Testing

Minimum test coverage: 80%
Write unit tests for all new functionality
Integration tests for critical workflows
Use pytest fixtures for test data

Adding a New E-commerce Platform

Create a new strategy in mcp_server/strategies/:

from .base import EcommerceStrategy

class YourPlatformStrategy(EcommerceStrategy):
    async def get_order(self, order_id: str) -> Optional[Order]:
        # Implementation here
        pass

Add tests in tests/unit/test_your_platform_strategy.py
Update the strategy factory to include your platform

📊 Environment Variables

Create a .env file based on .env.example:

# Application Settings
DEBUG=False
LOG_LEVEL=INFO

# Hugging Face (for deployment)
HF_TOKEN=your_token_here
HF_USERNAME=your_username
HF_SPACE_NAME=your_space_name

# E-commerce Platforms (future)
# SHOPIFY_API_KEY=
# MAGENTO_API_URL=

🚀 Deployment

Automatic Deployment

This project is configured for automatic deployment to Hugging Face Spaces:

Push to the main branch
GitHub Actions will run tests and quality checks
If all checks pass, the app deploys to Hugging Face Spaces

Manual Deployment

To deploy manually to Hugging Face Spaces:

# Add Hugging Face remote
git remote add space https://huggingface.co/spaces/SlavPilus/mpc-for-commerce-platforms

# Push to deploy
git push space main

🧪 Running Specific Commands

# Run only unit tests
pytest tests/unit/

# Run with coverage report
pytest --cov=mcp_server --cov=ui --cov-report=html

# Run linting
ruff check . --fix

# Format imports
isort .

# Type checking
mypy mcp_server ui --strict