SM

slavpilus/mcp

开发工具

本页由 AI 翻译,技术细节请以原文为准。 查看原文

7 stars 1 forks 质量 65 趋势 15MIT

MCP for Commerce Platforms

概览

Enneagora is a Universal E-commerce Customer Support Assistant using the Model Context Protocol (MCP) that provides a platform-agnostic solution for customer support across different e-commerce platforms. This comprehensive MCP server can be integrated with Claude Desktop or any MCP-compatible client to handle all aspects of customer inquiries. - : Dual MCP server implementation using both Gradio and FastMCP with SSE and STDIO transports - : - : get_order_status, cancel_order, process_return, track_package - : get_support_info, get_return_policy, get_shipping_info, get_contact_information - : get_size_guide, get_warranty_information, get_product_care_info - : get_payment_information, get_account_help, get_loyalty_program_info - : Strategy pattern for easy integration with any e-commerce platform - : Intelligent test data system with pattern-based order behavior - : Gradio MCP server for web deployment, FastMCP for Claude Desktop STDIO integration - : CI/CD pipeline with automated...

README

以下为原文 README 节选,完整内容请查看原文。


title: Enneagora - E-commerce MCP Server emoji: 🛍️ colorFrom: blue colorTo: purple sdk: gradio sdk_version: 5.33.0 app_file: main.py pinned: true license: mit tags:

  • mcp-server-track
  • cuustomer support
  • commerce
  • e-commerce

Enneagora - E-commerce MCP Server

Enneagora is a Universal E-commerce Customer Support Assistant using the Model Context Protocol (MCP) that provides a platform-agnostic solution for customer support across different e-commerce platforms. This comprehensive MCP server can be integrated with Claude Desktop or any MCP-compatible client to handle all aspects of customer inquiries.

🚀 Features

  • MCP-Compliant: Dual MCP server implementation using both Gradio and FastMCP with SSE and STDIO transports
  • 14 Comprehensive Customer Support Tools:
    • Order Management: get_order_status, cancel_order, process_return, track_package
    • Support Information: get_support_info, get_return_policy, get_shipping_info, get_contact_information
    • Product Guidance: get_size_guide, get_warranty_information, get_product_care_info
    • Account & Payment: get_payment_information, get_account_help, get_loyalty_program_info
  • Platform Agnostic: Strategy pattern for easy integration with any e-commerce platform
  • Dynamic Mock Data: Intelligent test data system with pattern-based order behavior
  • Dual Implementation Support: Gradio MCP server for web deployment, FastMCP for Claude Desktop STDIO integration
  • Production Ready: CI/CD pipeline with automated deployment to Hugging Face Spaces

📋 Prerequisites

  • Python 3.10 or higher
  • pip package manager
  • (Optional) Hugging Face account for deployment

🛠️ Installation

  1. Clone the repository:
git clone https://github.com/slavpilus/mcp.git
cd mcp
  1. Create and activate a virtual environment:
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
  1. Install dependencies:
pip install -r requirements.txt

🚀 Usage Options

Use the hosted Gradio MCP server on Hugging Face Spaces:

Gradio MCP Endpoint: https://huggingface.co/spaces/SlavPilus/mpc-for-commerce-platforms

Advantages:

  • Native Gradio MCP server implementation with mcp_server=True
  • No local setup required
  • Always up-to-date with latest features
  • Perfect for MCP-compatible clients and integrations
  • Seamless Hugging Face Spaces deployment

Gradio MCP Server (local development)

python main.py

The Gradio MCP server starts on http://localhost:7860 with MCP SSE endpoint at http://localhost:7860/gradio_api/mcp/sse.

FastMCP Claude Desktop Integration (STDIO)

Step 1: Configure Claude Desktop

macOS: Edit ~/Library/Application Support/Claude/claude_desktop_config.json Windows: Edit %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
在 GitHub 查看完整 README

安装

docker run -p 7860:7860 enneagora
新手?先看 mcpskill.org 教程 →

配置

{ "mcpServers": { "enneagora": { "command": "python", "args": ["/full/absolute/path/to/mcp/main_stdio.py"], "env": {} } } }