Shopping_Agent_Using_MCP_Server

The Shopping_Agent_Using_MCP_Server is an AI-powered shopping assistant that uses the Groq LLM and MCP to perform real-time shopping searches, compare products and services, and provide price guidance. It relies on MCP-enabled search engines (Playwright, Airbnb, and DuckDuckGo search servers) to fetch up-to-date information from supported shopping platforms. You can start the Python-based assistant, which will interact with these MCP endpoints to gather and summarize product data, helping users make smarter buying decisions. Typical workflows include query-based product searches, feature analysis, and price comparison across different vendors.

To use the MCP-backed capabilities, ensure your MCP configuration (browser_mcp.json) is in place and that the GROQ_API_KEY is available in your environment. The tool supports commands to manage context and session state, enabling context-aware conversations and resumable searches. When asking for product recommendations, the agent will run searches, analyze features, compare options, and present recommendations with provenance from the MCP search results.

Prerequisites:

• Python 3.8+ and npm/node installed
• Access to GROQ API key
• Git installed

Step-by-step installation:

1. Clone the repository and enter the project folder:

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

2. Create and activate a virtual environment (optional but recommended):

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

3. Install Python dependencies:

pip install -r requirements.txt

4. Install MCP Node.js dependencies globally (for MCP search servers):

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

5. Set up environment variables (example):

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

6. Prepare MCP configuration file (example):

{
  "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"]
    }
  }
}

7. Start the assistant:

python shopping_assistant.py

8. Ensure your browser MCP configuration path is set in the code if needed, for example:

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

Tips and troubleshooting: ensure internet access for MCP searches and GROQ API usage. If a search fails, MCP can retry or fall back; you can adjust retries and delay settings in your MCP config. Keep the GROQ_API_KEY secure and loaded in your environment (.env). The Node MCP servers (Playwright, Airbnb, DuckDuckGo) are used to drive browser-based searches across supported platforms; make sure Node.js and npm are installed and that the MCP packages are accessible. If you encounter MCP mismatch errors, verify that the browser_mcp.json structure matches the expected format and that the commands/args align with your environment. The tool supports context commands to view the latest summary and status commands to check rate limits.