Labsco
markswendsen-code logo

Strider Amazon

β˜… 1

from markswendsen-code

MCP server for Amazon shopping - AI agents can search products, check prices, add to cart, and manage shopping lists.

πŸ”₯πŸ”₯πŸ”₯βœ“ VerifiedFreeQuick setup

@striderlabs/mcp-amazon

npm version License: MIT

Amazon MCP Server by Strider Labs β€” give AI agents the ability to search products, manage your cart, place orders, and track shipments on Amazon via browser automation.

Features

  • Product Search β€” search Amazon with full result details (ASIN, price, ratings, Prime badge)
  • Product Details β€” fetch complete product info by ASIN or URL
  • Cart Management β€” add items, view cart, clear cart
  • Order Placement β€” preview and place orders with dual-confirmation safety
  • Order Tracking β€” track shipments with status and carrier info
  • Order History β€” retrieve past orders
  • Prime Status β€” check Prime membership and benefits
  • Address Management β€” set delivery address
  • Session Persistence β€” cookies saved to ~/.strider/amazon/ across sessions
  • Stealth Mode β€” random delays, user agent rotation, webdriver masking to reduce bot detection

Available Tools

ToolDescription
amazon_statusCheck login status and session info
amazon_loginInitiate login flow (returns URL + instructions)
amazon_logoutClear session and cookies
amazon_searchSearch products by keyword
amazon_get_productGet product details by ASIN or URL
amazon_add_to_cartAdd product to cart (ASIN, URL, or query)
amazon_view_cartView cart contents and subtotal
amazon_clear_cartRemove all items from cart
amazon_preview_orderPreview order before placing
amazon_place_orderPlace order (requires confirm=true)
amazon_track_orderTrack order by ID
amazon_get_ordersGet order history
amazon_prime_checkCheck Prime membership status
amazon_set_addressSet delivery address

Authentication Flow

Amazon requires manual login (headless browsers cannot complete Amazon's full auth flow including 2FA):

  1. Run amazon_login β€” it returns https://www.amazon.com/ap/signin
  2. Open that URL in your browser and log in with your Amazon credentials
  3. Complete any 2-factor authentication
  4. Run amazon_status to verify the session is detected
  5. Cookies are saved to ~/.strider/amazon/cookies.json for future sessions

Order Safety

amazon_place_order requires confirm: true to actually place an order:

  • Without confirm: true β€” returns a preview (same as amazon_preview_order)
  • With confirm: true β€” places the order immediately

Never set confirm: true without explicit user consent.

Bot Detection

Amazon has aggressive bot detection. This server includes:

  • Random delays between actions (500–2000ms)
  • User agent rotation (Chrome/Safari on macOS/Windows)
  • Webdriver property masking
  • Browser plugin/language spoofing
  • Proper viewport and screen resolution

If you receive a CAPTCHA error: visit amazon.com in your regular browser, complete the CAPTCHA, then retry. Cookies will be re-used in subsequent calls.

Technical Details

  • Runtime: Node.js 18+, ES modules
  • Browser: Playwright Chromium (headless)
  • Transport: MCP stdio
  • Session storage: ~/.strider/amazon/

Development

git clone https://github.com/striderlabs/mcp-amazon
cd mcp-amazon
npm install
npx playwright install chromium
npm run build
npm start