Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@SmartCustomerSupportMCP check the status of my recent order #ORD-789123"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
这是一个基于MCP框架的智能客服系统示例项目，用于演示如何构建和部署智能客服应用。
文档：https://mp.weixin.qq.com/s/gz3ZL_3XD8sfxustNQvK2g
智能问答服务
人工客服转接
订单信息查询
产品知识库管理
Related MCP server: ShopBot AI MCP Server
Python >= 3.10
MCP框架 >= 1.6.0
创建并激活虚拟环境（推荐）：
uv venv
source .venv/bin/activate # Linux/macOS安装依赖：
uv pip install .运行
以stdio方式运行，需要以--stdio启动
uv --directory /opt/apps/python_project/SmartCustomerSupportMCP run mcp-smart-customer-support --stdioor
python start.py --stdio以sse方式运行，直接启动即可,默认端口9000
uv --directory /opt/apps/python_project/SmartCustomerSupportMCP run mcp-smart-customer-supportor
python start.py stdio方式使用inspector：
npx @modelcontextprotocol/inspector uv --directory /opt/apps/python_project/SmartCustomerSupportMCP run mcp-smart-customer-support --stdio使用Vscode或Claude等桌面应用
{
"mcpServers": {
"SmartCustomerSupportMCP": {
"command": "uv",
"args": [
"--directory",
"/opt/apps/python_project/SmartCustomerSupportMCP",
"run",
"mcp-smart-customer-support",
"--stdio"
]
}
}
} 增加环境变量信息
{
"mcpServers": {
"SmartCustomerSupportMCP": {
"command": "uv",
"args": [
"--directory",
"/opt/apps/python_project/SmartCustomerSupportMCP",
"run",
"mcp-smart-customer-support",
"--stdio"
],
"env": {
"MYSQL_HOST": "192.168.xxx.xxx",
"MYSQL_PORT": "3306",
"MYSQL_USER": "root",
"MYSQL_PASSWORD": "root",
"MYSQL_DATABASE": "a_llm",
"MYSQL_ROLE": "admin"
}
}
}
}
src/mcp_smart_customer_support/
├── __init__.py # 包初始化文件
├── mcp_server.py # MCP服务器实现
├── human_customer_service.py # 人工客服处理模块
├── order_operations.py # 订单操作相关功能
└── product_knowledge.py # 产品知识库管理ggguo (admin@precariat.tech)
本项目采用MIT许可证。
This server cannot be deployed
Hybrid human + AI expertise for faster, trusted answers and decisions via MCP Server.
Connect e-commerce and marketing data to AI assistants via MCP.
Team knowledge from 20 connectors, served to any MCP agent — classified, scored, access-controlled.
Marketing intelligence MCP server providing campaign performance data and analytics tools.
