amazon-lyr
Provides an Amazon research and shopping integration, enabling product search, product details, reviews, cart management, wishlist access, and order tracking through a logged-in browser session.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@amazon-lyrSearch for noise-cancelling headphones under $300, then compare the top 3 and show critical reviews."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An agent session, start to finish
This is one real conversation with an agent running amazon-lyr — no steps hidden:
1. search_products("noise cancelling headphones", max_price=300, min_rating=4)
2. review_insights("B0X1234567") # star spread + keyword themes
3. search_in_reviews("B0X1234567", query="broke") # what actually breaks?
4. add_to_cart("B0X1234567", quantity=1)
5. checkout_preview() # totals + address + payment, nothing bought
6. place_order(confirm="PLACE_ORDER") # only after the user said "buy it"
✓ order placed · #111-2223334-5556667
7. track_shipment("111-2223334-5556667")
8. initiate_return("111-2223334-5556667", reason="defective", asin_hint="…")
9. list_returns() # refund status confirmedEvery step is a typed MCP tool call. The buying step is deliberately hard to fire by accident — see Safety model.
Related MCP server: Amazon MCP Server
Why it's different
No API keys | Speaks Amazon's own web endpoints over |
Full lifecycle | Not just scraping: cart mutations, wishlist writes, checkout with confirmation parsing, returns wizard, cancellations |
Agent-native errors | CAPTCHAs, sign-out redirects and soft throttles surface as typed errors with recovery hints ( |
How it works
browser cookies ──▶ AmazonClient (curl_cffi, captcha-aware)
│
▼
bs4 parsers ──▶ normalized dicts ──▶ 21 FastMCP tools
(readOnly / destructive annotations)Auth is your own session: amazon-lyr login imports cookies from Chrome,
Brave, Firefox, Edge or Zen via obscura-core,
or from an explicit JSON export. Reads need the login token; cart, orders,
returns and checkout also need the session context cookies.
Install
# Persistent install — uv tool (isolated; bootstraps uv on clean systems)
curl -sSL https://raw.githubusercontent.com/ishan-parihar/amazon-lyr/main/install.sh | bash
# Zero-install run without persistence:
uvx --from git+https://github.com/ishan-parihar/amazon-lyr amazon-lyr --versionThen authenticate once and serve:
amazon-lyr login --browser chrome # or: --cookies-file cookies.json
amazon-lyr search "mechanical keyboard" # shell works immediately
amazon-lyr serve # MCP server (stdio){
"mcpServers": {
"amazon": {
"command": "amazon-lyr",
"args": ["serve"]
}
}
}Tools (21)
Category | Tools |
Search |
|
Product |
|
Reviews |
|
Cart |
|
Wishlist |
|
Orders |
|
Returns |
|
Buying |
|
Danger zone |
|
Session |
|
Safety model
Money moves through exactly two gates:
Session gate — every mutation requires full login cookies (
at-main+session-id/ubid-main). Reads-only sessions are refused before any request is made.Consent gate —
place_orderrefuses to run unless passed the exact literalconfirm="PLACE_ORDER". The intended flow is: preview for the user → user approves → then pass the literal.cancel_orderandinitiate_returnare similarly annotated as destructive/non-idempotent so agent frameworks treat them accordingly.
Card verification (OTP / 3-D Secure) is detected mid-checkout and reported
as needs_verification with browser instructions — never guessed through.
Limits
Honest ceilings, all surfaced as typed errors instead of wrong data:
CAPTCHA walls — account-area pages are stricter than the catalog; re-import fresh cookies or wait it out (
CaptchaErrorincludes hints)Soft throttles — sub-3-second cadences get silent empty grids; responses carry
possibly_throttled: truewhen suspectedGeo price variants — some variants render prices client-side; search falls back to text-scanning,
get_productstays authoritativeNo auto-buy without consent — by design; checkout demands the explicit confirm literal and user approval
Development
git clone https://github.com/ishan-parihar/amazon-lyr && cd amazon-lyr
uv sync --extra dev
uv run ruff check . && uv run pytest -qArchitecture notes, invariants, and the release process live in AGENTS.md.
License
MIT © Ishan Parihar
This server cannot be deployed
Maintenance
Related MCP Connectors
Real-time Amazon product, seller, and search data for AI agents across 21 marketplaces.
Product search for AI agents: Amazon + Shopify, cart-to-checkout buy path. Pay-per-call, no API key.
Web search, browser automation, scraping, crawling and CAPTCHA solving for AI agents.
Shopping MCP for AI agents: search, compare, Amazon buy links. Auto-register.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to search products, manage shopping carts, place orders, and retrieve order history from Amazon and Target accounts.2MIT
- AlicenseNot gradedqualityDmaintenanceEnables interaction with Amazon services through AI assistants, allowing users to search products, manage their cart, view order history, and place orders using natural language.6 npmMIT
- FlicenseNot gradedqualityDmaintenanceEnables scraping Amazon product details and searching for products on Amazon through natural language queries. No API keys required as it scrapes publicly available Amazon pages.10-
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with your personal Amazon cart through browser automation, allowing search, add to cart, and view cart functionalities.4 npm22MIT