Amazon

You run an MCP server that scrapes Amazon product pages and enables keyword-based product searches. It exposes two practical tools you can call from an MCP client: scraping a specific product and searching Amazon by a query. This server runs locally and does not require API keys, giving you direct access to publicly available data for integration and automation workflows.

How to use

You interact with the server through an MCP client by calling the available tools. Use scrape_product(product_url) to fetch details such as name, price, image, rating, reviews, availability, and description for a given Amazon product URL. Use search_products(query, max_results) to perform a keyword search on Amazon and return a list of results. You can combine these tools in natural language prompts to fetch data and use the results in your application workflows.

How to install

Prerequisites: you need Python installed on your system. You will also create a virtual environment and install dependencies.

git clone https://github.com/r123singh/amazon-mcp-server.git

cd amazon-mcp-server

python -m venv venv

# Activate the virtual environment
# Linux/macOS
source venv/bin/activate
# Windows
venv\Scripts\activate

pip install -r requirements.txt

# No API keys or tokens are required.

Configuration and running

Configure the MCP server by creating a JSON configuration that tells your MCP client how to launch the server. The example below shows how to run the server using a Python command from within a virtual environment and point to the server script.

{
  "mcpServers": {
    "amazon": {
      "command": "C:\\path\\to\\venv\\Scripts\\python.exe",
      "args": [
        "C:\\path\\to\\amazon-mcp-server\\server.py"
      ]
    }
  }
}

Notes

No API keys or authentication are required. The server scrapes publicly available Amazon product pages and search results. For best results, use valid Amazon product URLs and clear search queries.

Security and maintenance

Since this server scrapes publicly accessible pages, ensure you comply with Amazon's terms of service and respect rate limits. Regularly update dependencies in your Python virtual environment and review any logs for unexpected activity.

Troubleshooting

If the server does not start, verify that the path to the Python executable and the server script is correct in the configuration. Ensure your virtual environment is activated before launching the MCP client. Check that there is network access to Amazon as needed for scraping and that your MCP client is configured to communicate with the running server.

Available tools

scrape_product

Scrape product details from a given Amazon product URL, including name, price, image, rating, reviews, availability, and description.

search_products

Search Amazon by keyword and return a list of results with up to max_results items.