AI Shopping Assistant

A conversational AI shopping assistant for web-based product discovery and decision-making.

An intelligent, conversational shopping assistant powered by the Groq AI model and Model Context Protocol (MCP) for smart web-based product discovery and decision-making.

TheAI Shopping Assistantis an interactive, AI-powered chatbot that helps users makesmarter shopping decisions. Backed byxAI’s Groq LLMand theModel Context Protocol (MCP), it can:

- 🧠 Understand natural language queries
- 🔎 Conduct real-time searches on shopping platforms
- 🛒 Compare products, services, and features
- 💸 Provide price guidance and recommendations

Whether you're choosing between phones, comparing streaming services, or searching for the best air purifier under a budget—this assistant is yourultimate shopping buddy.

git clone <repository-url> cd ai-shopping-assistant

2. Set Up a Virtual Environment (Optional)

python -m venv venv source venv/bin/activate # Windows: venv\Scripts\activate

Make sureNode.jsandnpmare installed:

npm install -g @playwright/mcp @openbnb/mcp-server-airbnb duckduckgo-mcp-server

Create a.envfile in the root directory:

echo "GROQ_API_KEY=your-api-key-here" > .env

Ensure you have a validbrowser_mcp.jsonin your MCP directory (e.g.,D:\mcp\mcpdemo\):

{ "mcpServers": { "playwright": { "command": "npx", "args": ["@playwright/mcp@latest"] }, "airbnb": { "command": "npx", "args": ["-y", "@openbnb/mcp-server-airbnb"] }, "duckduckgo-search": { "command": "npx", "args": ["-y", "duckduckgo-mcp-server"] } } }

self.config_file = r"path/to/your/browser_mcp.json"

🛒 You: Best laptop for programming under $1000 🤖 Assistant: 🔍 Searching... (attempt 1/3) ✅ Successfully retrieved current information [Laptop recommendations with specs and prices]

- exitorquit– End the session
- clear– Reset chat history
- context– View recent conversation summary
- status– Check last search time and rate limits

ai-shopping-assistant/ ├── shopping_assistant.py # Main assistant logic ├── requirements.txt # Python dependencies ├── .env # Environment variables ├── browser_mcp.json # MCP config for search engines └── README.md # You're reading it!

Add the following to yourrequirements.txt:

langchain-grok==0.1.0 python-dotenv==1.0.0 requests==2.31.0 mcp-use==<latest-version>

- Requires internet connection for API and MCP search
- Prices may vary—verify with retailers
- Only predefined categories supported
- MCP setup requires proper Node.js configuration
- Offline fallbacks may offer limited depth

- 🛒 Real-time price scraping from major e-retailers
- 🧬 Personalized recommendations via user profiles
- 🖥️ Web-based UI for a seamless UX
- 🛠️ Enhanced MCP integration with more shopping portals

Contributions are welcome! To contribute:

git commit -m "Add your feature"

🧠AI + Shopping = Smarter ChoicesStart your intelligent shopping journey now with the AI Shopping Assistant.

Enable AI agents to get structured data from unstructured web with AgentQL.

Web scraping, crawling, and change detection with AI

Official Apify MCP server for AI agents to run Actors, extract website data, and automate web scraping and crawling workflows.

1GB Free Trial, World's Leading Proxy Service Platform, Efficient Data Collection

Discover, extract, and interact with the web - one interface powering automated access across the public internet.

Automate browser interactions in the cloud (e.g. web navigation, data extraction, form filling, and more)

Easy web data access. Simplified retrieval of information from websites and online sources.

Adds powerful web scraping and search capabilities to LLM clients like Cursor and Claude.

Real-time web data, structured for agents