E-commerce MCP Server
Enables management of e-commerce operations including products, customers, and orders with full CRUD capabilities, plus data analysis features like sales summaries, top products/customers reports, and inventory tracking.
README
E-commerce MCP Server
A FastMCP server for managing products, customers, and orders with full CRUD operations and data analysis capabilities.
Installation
# Create and activate virtual environment
python3 -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install dependencies
pip install fastmcp sqlalchemy aiosqlite
Running the Server
# Using fastmcp CLI
fastmcp run ecommerce_server.py
# Or directly with Python
python ecommerce_server.py
Configuring with Claude Desktop
Add this to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"ecommerce": {
"command": "/path/to/venv/bin/python",
"args": ["/path/to/ecommerce_server.py"],
"env": {
"ECOMMERCE_DB_PATH": "/path/to/ecommerce.db"
}
}
}
}
Available Tools (25 total)
Product Management
| Tool | Description |
|---|---|
add_product |
Add a new product to inventory |
get_product |
Get product by ID or SKU |
list_products |
List products with filtering (category, stock level) |
update_product |
Update product details |
delete_product |
Soft delete (deactivate) a product |
update_stock |
Add or subtract stock quantity |
search_products |
Search products by name/description |
Customer Management
| Tool | Description |
|---|---|
add_customer |
Add a new customer |
get_customer |
Get customer by ID or email |
list_customers |
List customers with filtering |
update_customer |
Update customer details |
delete_customer |
Soft delete (deactivate) a customer |
search_customers |
Search customers by name/email |
Order Management
| Tool | Description |
|---|---|
create_order |
Create a new order for a customer |
add_order_item |
Add a product to an order |
remove_order_item |
Remove a product from an order |
get_order |
Get order by ID or order number |
list_orders |
List orders with filtering (customer, status, date range) |
update_order_status |
Update order status (pending → confirmed → shipped → delivered) |
Data Analysis & Reporting
| Tool | Description |
|---|---|
get_sales_summary |
Revenue, order count, average order value for a period |
get_top_products |
Top selling products by quantity and revenue |
get_top_customers |
Top customers by spend and order count |
get_inventory_report |
Stock levels, out-of-stock items, category breakdown |
get_customer_order_history |
Complete order history for a customer |
get_profit_analysis |
Profit margins by product (requires cost data) |
Example Usage
Adding Products
"Add a product: iPhone 15 Pro, SKU: IP15PRO, price $999, cost $750, 50 in stock, category Electronics"
Managing Customers
"Add customer John Doe, email john@example.com, phone 555-1234"
"Find all customers in New York"
Creating Orders
"Create an order for customer ID 1"
"Add 2 units of product ID 3 to order ID 1"
"Mark order 1 as shipped"
Data Analysis
"Show me the sales summary for this month"
"What are the top 5 selling products?"
"Which products are low on stock?"
"Show profit analysis for Q4"
Database
The server uses SQLite by default. The database file location can be configured via the ECOMMERCE_DB_PATH environment variable.
Schema
- Products: id, name, description, sku, price, cost, quantity_in_stock, category, is_active
- Customers: id, email, first_name, last_name, phone, address, city, state, postal_code, country, is_active
- Orders: id, customer_id, order_number, status, total_amount, shipping_address, notes
- OrderItems: id, order_id, product_id, quantity, unit_price
Order Statuses
pending- Order created, awaiting confirmationconfirmed- Order confirmed, stock reservedshipped- Order shipped to customerdelivered- Order deliveredcancelled- Order cancelled, stock restored
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。