Labsco
sharavanask logo

Amazon Product Search

from sharavanask

An AI-powered server for Amazon product search and recommendations.

🔥🔥✓ VerifiedFreeNeeds API keys
#automation

Amazon Product Search MCP Server

The site is live here ! : https://shopassist-sharavana.streamlit.app/

An MCP (Model Context Protocol) server that provides AI-powered Amazon product search and recommendations using FastMCP.

Features

  • 🔍 Smart product search with Amazon API
  • 🤖 AI-powered product recommendations using Hugging Face
  • 💰 Price range filtering
  • 📋 Feature-based matching
  • 🎯 Tailored recommendations for Small/Medium Enterprises

Client Options

We provide multiple client implementations to interact with your MCP server:

1. Python Interactive Client (client.py)

A full-featured Python client with examples and interactive mode.

python client.py

Features:

  • Pre-built examples (laptops, smartphones)
  • Interactive search mode
  • Real-time communication with MCP server

2. Command Line Interface (cli_client.py)

Quick command-line searches for automation and scripting.

# Basic search
python cli_client.py "laptop"

# With features and price range
python cli_client.py "laptop" --features "8GB RAM, SSD storage" --min-price 30000 --max-price 80000

# Smartphone search
python cli_client.py "smartphone" --features "good camera, 5G" --min-price 15000 --max-price 50000

Arguments:

  • product: Product to search for (required)
  • --features, -f: Specific features to look for
  • --min-price, -min: Minimum price in rupees
  • --max-price, -max: Maximum price in rupees

3. Web Interface (web_client.py)

A beautiful web interface with REST API backend.

# Install additional dependencies
pip install fastapi uvicorn

# Run the web server
python web_client.py

Then open http://localhost:8000 in your browser for a user-friendly interface.

API Endpoints:

  • GET /: Web interface
  • POST /search: REST API for product search
  • GET /health: Health check

4. MCP CLI Integration

You can also use the MCP CLI to interact with your server:

# Install MCP CLI if not already installed
pip install mcp

# Connect to your server
mcp connect stdio -- python main.py

Integration with Claude Desktop

To use this MCP server with Claude Desktop, add this configuration to your claude_desktop_config.json:

{
  "mcpServers": {
    "amazon-search": {
      "command": "python",
      "args": ["path/to/your/main.py"],
      "env": {}
    }
  }
}

Development

Adding New Features

  1. Add new tools in server/buy.py using the @mcp.tool() decorator
  2. Update client code to use new tools
  3. Test with the interactive client first

Testing

# Test the server directly
python -c "from server.buy import mcp; print('Server loads successfully')"

# Test with the interactive client
python client.py

Architecture

┌─────────────────┐    ┌─────────────────┐    ┌─────────────────┐
│   MCP Client    │◄──►│   MCP Server    │◄──►│  External APIs  │
│  (Your Choice)  │    │   (FastMCP)     │    │ (Amazon/HF AI)  │
└─────────────────┘    └─────────────────┘    └─────────────────┘
       │                        │                        │
       ▼                        ▼                        ▼
┌─────────────────┐    ┌─────────────────┐    ┌─────────────────┐
│  • client.py    │    │ • Tool: getdata │    │ • Amazon Search │
│  • cli_client   │    │ • AI Agent      │    │ • HuggingFace   │
│  • web_client   │    │ • FastMCP       │    │ • Recommendations│
│  • Claude       │    │                 │    │                 │
└─────────────────┘    └─────────────────┘    └─────────────────┘