ποΈ MCP - MCP for Commerce Platforms - Universal E-commerce Customer Support Assistant
About
It is a platform-agnostic customer support assistant that connects to any e-commerce platform through pluggable strategies, using the MCP (Model Context Protocol) server and Gradio for the user interface. It is built for developers and support teams who need a singleβ¦
Details
- Author
- slavpilus
- Downloads
- 371
- Categories
- AI
Jump to
- Order management: track orders, check status, view history
- Returns and refunds: initiate returns, process refunds
- Order cancellations: quick and easy cancellations
- Conversational interface using natural language
- Platform-agnostic, extensible via a strategy pattern
- Autoβdeployment to Hugging Face Spaces
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
ποΈ MCP - MCP for Commerce Platforms - Universal E-commerce Customer Support AssistantCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Clone the repository, run the setup script (scripts/setup_dev.sh) or manually create a virtual environment, install dependencies from requirements-dev.txt, copy .env.example to .env and configure it, then run python app.py. The application will be available at http://localhost:7860.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"\ud83d\udecd\ufe0f mcp - mcp for commerce platforms - universal e-commerce customer support assistant": {
"mcp-slavpilus": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}
}
}
McpServers
{
"mcp-slavpilus": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}
ποΈ 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.
π― Features
- π¦ Order Management: Track orders, check status, view history
- π Returns & Refunds: Initiate returns, process refunds seamlessly
- β Cancellations: Quick and easy order cancellations
- π¬ Natural Language: Conversational interface for customer support
- π Platform Agnostic: Extensible to any e-commerce platform
- π Auto-Deploy: Continuous deployment to Hugging Face Spaces
ποΈ Architecture
The system uses a Strategy Pattern to abstract different e-commerce platforms:
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β Gradio UI Layer β
β (Customer Support Conversational Interface) β
βββββββββββββββββββββββββββββββ¬ββββββββββββββββββββββββββββ
β
βββββββββββββββββββββββββββββββΌββββββββββββββββββββββββββββ
β MCP Server Core β
β (Order Management, NLP Processing, Context Engine) β
βββββββββββββββββββββββββββββββ¬ββββββββββββββββββββββββββββ
β
βββββββββββββββββββββββββββββββΌββββββββββββββββββββββββββββ
β E-commerce Strategy Interface β
β (MockData, Shopify, Magento, WooCommerce, etc.) β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
π Quick Start
Prerequisites
- Python 3.10 or higher
- Git
- Virtual environment tool (venv)
Installation
1. Clone the repository
git clone https://github.com/slavpilus/mcp.git
cd mcp
2. 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
3. Configure environment variables
cp .env.example .env
# Edit .env with your configuration
4. Run the application
python app.py
The application will be available at http://localhost:7860
π οΈ Development
Project Structure
mcp/
βββ .github/workflows/ # CI/CD pipelines
βββ mcp_server/ # Core MCP server implementation
β βββ strategies/ # E-commerce platform strategies
β βββ models/ # Data models
β βββ utils/ # Utility functions
βββ ui/ # Gradio UI components
βββ tests/ # Test suite
βββ app.py # Main Gradio application
βββ requirements.txt # Python dependencies
Development Workflow
1. Activate virtual environment
source venv/bin/activate # macOS/Linux
# or
venv\Scripts\activate # Windows
2. Make your changes
- Follow the existing code style
- Add tests for new functionality
- Update documentation as needed
3. Run code quality checks
# Format code
black .
isort .
# Run linter
ruff check .
# Type checking
mypy mcp_server ui
4. Run tests
# Run all tests with coverage
pytest
# Run specific test file
pytest tests/unit/test_strategies.py
# Run with verbose output
pytest -v
5. 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
1. 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
2. Add tests in tests/unit/test_your_platform_strategy.py
3. Update the strategy factory to include your platform
π Environment Variables
Create a .env file based on .env.example:
```env
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
