amazon

This MCP server exposes two primary capabilities for interacting with Amazon data: scraping product details and searching for products by keyword. The scrape_product tool fetches public product pages and extracts information such as name, price, image, rating, reviews, availability, and description. The search_products tool queries Amazon with a keyword and returns a list of matching results up to a specified limit. Once the MCP server is running, you can use the standard MCP client to invoke these tools via natural language prompts, for example: “Get details for this Amazon product: <URL>” or “Search Amazon for 'wireless headphones', show top 3 results.” The server runs locally (via the configured Python environment) and processes requests by using the provided tools to gather publicly available data from Amazon pages.

To use the server, configure your mcp.json to point to the local server entry point, start the MCP client, and issue natural language commands that map to the available tools. The server is designed to operate without API keys, relying on publicly accessible product and search pages on Amazon.

Prerequisites:

• Python 3.8+ installed on your system
• Git installed
• Basic command line familiarity

Installation steps:

1. Clone the repository: git clone https://github.com/r123singh/amazon-mcp-server.git

2. Navigate to the project directory: cd amazon-mcp-server

3. Create a Python virtual environment: python -m venv venv

4. Activate the virtual environment:

   • macOS/Linux: source venv/bin/activate
   • Windows: venv\Scripts\activate

5. Install dependencies: pip install -r requirements.txt

6. Create the MCP configuration file (mcp.json) with the following structure: { "mcpServers": { "amazon": { "command": "python", "args": ["server.py"] } } }

   Note: If you are running inside a virtual environment, ensure the correct python executable is invoked (e.g., path/to/venv/bin/python or path\to\venv\Scripts\python.exe).

7. Start the MCP client and connect to the local server as per your MCP client’s instructions. No API keys or tokens are required for this server.

Tips and notes:

• No API key is required; the server scrapes publicly available Amazon product and search pages.
• Ensure you provide valid Amazon product URLs for scraping and clear, query-based keywords for searching to improve results.
• If the server cannot reach Amazon pages due to network restrictions, check your network proxy settings and ensure outbound access is allowed.
• When configuring the mcp.json, use absolute paths to the Python executable and server script if needed to avoid path resolution issues.
• If you encounter Python environment issues, re-create the virtual environment and reinstall dependencies using the steps above.
• For debugging, run server.py directly (in the activated venv) to verify that the server starts without errors before integrating with an MCP client.