Amazon Product Search

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

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

# Using uv (recommended) uv sync # Or using pip pip install -r requirements.txt

# Activate your virtual environment source .venv/bin/activate # On Windows: .venv\Scripts\activate # Run the server python main.py

# 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

# Install additional dependencies pip install fastapi uvicorn # Run the web server python web_client.py

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

# Install MCP CLI if not already installed pip install mcp # Connect to your server mcp connect stdio -- python main.py

{ "product": "laptop", "specific_features": "8GB RAM, SSD storage, good for programming", "min_price": 30000, "max_price": 80000 }

{ "product": "smartphone", "specific_features": "good camera, long battery life, 5G support", "min_price": 15000, "max_price": 50000 }

{ "product": "wireless headphones", "specific_features": "noise cancellation, comfortable", "min_price": 1000, "max_price": 5000 }

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

- Import errors: Make sure you're in the correct virtual environment
- API failures: Check your API keys and internet connection
- Connection issues: Ensure the MCP server is running before starting clients

- "No result": Usually indicates API issues or no products found
- "Connection refused": MCP server is not running
- "Tool not found": Server initialization issue
- Add new tools inserver/buy.pyusing the@mcp.tool()decorator
- Update client code to use new tools
- Test with the interactive client first

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

┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐ │ 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 │ │ │ │ │ └─────────────────┘ └─────────────────┘ └─────────────────┘

This project is open source. Please ensure you comply with the terms of service of the APIs used (Amazon, RapidAPI, Hugging Face).

Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.

Search and get install details on MCP servers directly from your agent -- a unified marketplace index.

Argentina's trust-first local services marketplace. Six read-only tools to search verified professionals and deep-link into on-platform task creation. │

Discover ethical, origin-verified products from the US and Canada by country, category, or brand.

Real-time search API for AI agents. Search Google, Amazon, Walmart, and YouTube with 9 tools -- product search, product details, video search, transcripts, and more. Build price comparison agents, retail arbitrage tools, content research pipelines, and brand monitors. 500 free credits/month.

Connects AI to Facebook Marketplace, Ebay, Poshmark, and Depop to find you the best deals

Google for agentic fashion shopping/discovery. Indexed fashion brand e-coms. Semantic search.

Real-time product search and price comparison across 15+ SG/SEA/US merchants (161M+ products) via MCP server and REST API

DesiDime MCP Server is the AI powered Deal & Coupon Search: Search deals, coupons, stores, and more from India's largest shopping community directly in Claude, ChatGPT, Cursor, or any MCP-compatible AI assistant.

Fetch, convert, and search AWS documentation pages, with recommendations for related content.

Search campgrounds around the world on campertunity, check availability, and provide booking links.