Online Boutique AI Assistant Server

PyPI version Python License: MIT Downloads

Model Context Protocol (MCP) Server for Online Boutique AI Assistant

Expose microservices through the standardized Model Context Protocol, enabling any MCP client to access complete e-commerce functionality.

📦 Available on PyPI

Table of Contents

1. Features
2. Architecture
3. Installation
4. Usage
5. Available Functions
6. Configuration
7. Development
8. Requirements
9. Use Cases
10. Contributing
11. License

Features

• Complete E-commerce: 18 microservice functions for products, cart, checkout, payments, shipping
• Standard MCP Protocol: Works with any MCP client (Claude, ChatGPT, custom tools)
• Google ADK Integration: Built using Google Agent Development Kit patterns
• Dynamic Configuration: Environment variable based configuration
• Production Ready: Comprehensive logging and error handling

Architecture

┌─────────────────┐    ┌──────────────────┐    ┌─────────────────────┐
│   MCP Client    │────│  MCP Server      │────│  Microservices      │
│ (Any LLM/Agent) │    │ (This Package)   │    │ (Online Boutique)   │
└─────────────────┘    └──────────────────┘    └─────────────────────┘

Installation

Install from PyPI:

pip install ai-boutique-assit-mcp

Or install from source:

git clone https://github.com/arjunprabhulal/ai-boutique-assit-mcp.git
cd ai-boutique-assit-mcp
pip install -e .

Usage

1. Start MCP Server

The server supports two modes of operation:

HTTP Mode (Web/API Access)

# Standalone HTTP server (default)
boutique-mcp-server --port 8080

# Or explicitly force HTTP mode
boutique-mcp-server --http --port 8081

Stdio Mode (ADK Integration)

# Force stdio mode for direct ADK integration
boutique-mcp-server --stdio

# ADK will automatically launch in stdio mode when using StdioConnectionParams

Available Options

boutique-mcp-server --help

# Options:
#   --port PORT    Port for HTTP mode (default: 8080)
#   --stdio        Force stdio mode (for ADK integration)
#   --http         Force HTTP mode (for web/API access)

2. Connect with ADK Agent

HTTP Connection (Manual Server Start)

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset, SseConnectionParams

agent = Agent(
    name="boutique_assistant",
    model="gemini-2.0-flash",
    instruction="You are a helpful e-commerce assistant.",
    tools=[
        McpToolset(
            connection_params=SseConnectionParams(
                url="http://localhost:8081/mcp"
            )
        )
    ]
)

Stdio Connection (Automatic Server Launch)

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset, StdioConnectionParams, StdioServerParameters

agent = Agent(
    name="boutique_assistant", 
    model="gemini-2.0-flash",
    instruction="You are a helpful e-commerce assistant.",
    tools=[
        McpToolset(
            connection_params=StdioConnectionParams(
                server_params=StdioServerParameters(
                    command="boutique-mcp-server",
                    args=["--stdio"],
                    env={
                        "PRODUCT_CATALOG_SERVICE": "localhost:3550",
                        "CART_SERVICE": "localhost:7070",
                        # Add other service endpoints as needed
                    }
                )
            )
        )
    ]
)

Available Functions

The MCP server exposes 18 e-commerce functions:

Products & Catalog

• list_products() - Browse all products
• search_products(query) - Search product catalog
• get_product(product_id) - Get product details
• get_product_with_image(product_id) - Product with image
• filter_products_by_price(max_price_usd) - Price filtering

Shopping Cart

• add_item_to_cart(user_id, product_id, quantity) - Add to cart
• get_cart(user_id) - View cart contents
• empty_cart(user_id) - Clear cart

Checkout & Orders

• place_order(user_id, currency, address, email, credit_card) - Complete purchase
• initiate_checkout() - Start checkout process

Shipping & Logistics

• get_shipping_quote(address, items) - Calculate shipping
• ship_order(address, items) - Arrange shipping

Payment & Currency

• charge_card(amount, credit_card) - Process payment
• get_supported_currencies() - Available currencies
• convert_currency(from_amount, to_currency) - Currency conversion

Communication

• send_order_confirmation(email, order) - Email confirmations

Marketing

• get_ads(context_keys) - Promotional content
• list_recommendations(user_id, product_ids) - Product suggestions

Configuration

Environment Variables

The server connects to Online Boutique microservices using these default endpoints (Kubernetes service names):

# Default endpoints (production/GKE environment)
PRODUCT_CATALOG_SERVICE="productcatalogservice:3550"
CART_SERVICE="cartservice:7070"
RECOMMENDATION_SERVICE="recommendationservice:8080"
SHIPPING_SERVICE="shippingservice:50051"
CURRENCY_SERVICE="currencyservice:7000"
PAYMENT_SERVICE="paymentservice:50051"
EMAIL_SERVICE="emailservice:5000"
CHECKOUT_SERVICE="checkoutservice:5050"
AD_SERVICE="adservice:9555"

For local testing, override with localhost endpoints:

export PRODUCT_CATALOG_SERVICE="localhost:3550"
export CART_SERVICE="localhost:7070"
export RECOMMENDATION_SERVICE="localhost:8080"
export SHIPPING_SERVICE="localhost:50051"
export CURRENCY_SERVICE="localhost:7000"
export PAYMENT_SERVICE="localhost:50052"
export EMAIL_SERVICE="localhost:5000"
export CHECKOUT_SERVICE="localhost:5050"
export AD_SERVICE="localhost:9555"

Development

Local Development

# 1. Clone the repository
git clone https://github.com/arjunprabhulal/ai-boutique-assit-mcp.git
cd ai-boutique-assit-mcp

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

# 3. Start MCP server
boutique-mcp-server --port 8081

# Or use Python module directly
python -m ai_boutique_assit_mcp.mcp_server --port 8081

# 4. Test with ADK (stdio mode)
adk run your_agent.py

# 5. Test with ADK (HTTP mode - start server first)
boutique-mcp-server --http --port 8081
# Then in another terminal: adk run your_agent.py

Build and Publish

# Build package
python -m build

# Publish to PyPI
python -m twine upload dist/*

Requirements

• Python: 3.9 or higher
• Google ADK: For MCP integration
• gRPC: For microservice communication
• Target microservices: Compatible gRPC services

Use Cases

• AI Agents: Connect any LLM to e-commerce microservices
• API Gateway: Unified access to distributed services
• Testing: Mock or test e-commerce workflows
• Integration: Standard protocol for microservice access
• Multi-platform: Use from Python, Node.js, any MCP client

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Repository: https://github.com/arjunprabhulal/ai-boutique-assit-mcp

1. Fork the repository
2. Create your feature branch
3. Commit your changes
4. Push to the branch
5. Create a Pull Request

License

MIT License - see LICENSE file for details.