About Amazon Orders
Amazon Orders is an unofficial MCP server for querying Amazon order history, items, payments, and related account records. It is for people using Claude or other MCP clients, with browser- or terminal-based sign-in and support for multiple Amazon sites.
Key features
- 01Browse orders by year, type, or time range
- 02Search items by product, order, address, or recipient
- 03Retrieve shipment tracking and invoices
- 04Read transactions, gift cards, and Prime charges
- 05Manage settings and check sign-in sessions
Use cases
- 01Find an order or its shipment tracking details
- 02Review spending and payment transactions
- 03Check gift card balances and activity
MCP support
Exposes Amazon order, shipment, invoice, and payment tools to MCP clients. It supports local stdio use and Streamable HTTP for remote clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
8Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| browser | any | No | Only when there's no browser to sign in with: the one the user chose, either one offered to download for them or a browser they already have installed. It's saved, so they're only asked once. |
Details
From the project README
amazon-orders-mcp is an unofficial MCP server for Amazon order history, line items,
and transactions, built on amazon-orders. It gives your AI assistant
tools for your Amazon account, available from Claude and any other MCP client.
The server never sees your credentials. When you sign in, a browser window opens on Amazon's own page, and the server reuses the session that leaves behind. It also runs on a server without a display, where you sign in from a terminal instead (see Remote Clients).
Note: This server reads its data through
amazon-orders, which works by parsing data from Amazon's consumer-facing website. As Amazon provides no official API to use, older versions may break at any time, so it's recommended that you use the latest version.
Installation
amazon-orders-mcp is available on PyPI and is run
with uvx, so there's nothing to install up front. Add it to your AI assistant:
Claude
Claude Desktop: download amazon-orders-mcp-<version>.mcpb from the
latest release and open it.
Claude Code:
claude mcp add amazon-orders -- uvx amazon-orders-mcp
ChatGPT
ChatGPT Desktop: in Settings → Plugins, add an MCP server of type STDIO, with uvx as the command and
amazon-orders-mcp as its argument.
Codex:
codex mcp add amazon-orders -- uvx amazon-orders-mcp
Other Clients
Any client that runs local MCP servers can use this JSON, or amazon-orders-mcp as the command if you've
installed it with pip install amazon-orders-mcp:
{
"mcpServers": {
"amazon-orders": {
"command": "uvx",
"args": ["amazon-orders-mcp"]
}
}
}
Remote Clients
For clients that connect to a server instead of running one, the server can also serve Streamable HTTP:
uvx amazon-orders-mcp --transport streamable-http
It listens at http://127.0.0.1:8000/mcp. See --help to change that, or to require a bearer token (required off
loopback). On a server without a display, sign_in can't open a browser window, so sign in there first with
uvx amazon-orders login, which asks for your username and password instead.
Docker
docker build -t amazon-orders-mcp .
docker run -i --rm -v amazon-orders:/home/app/.config/amazonorders amazon-orders-mcp
A container has no display, so sign in with the login target first. See the Dockerfile for how.
Basic Usage
Just ask your assistant about your orders, and it will use the following tools:
| Tool | Returns |
|---|---|
sign_in | Opens a browser window for you to sign in to Amazon, when you ask |
get_orders | A batch of orders by year, time filter or order type, optionally detailed |
search_orders | A batch of items by product, order number, address or recipient, any year |
get_order | One order, by order number |
get_tracking | A shipment's carrier and tracking number, from an order's shipment ID |
get_invoices | An order's printable summary, and any invoice PDFs the seller issues |
get_family_members | Amazon Household members whose orders you can view, like Teen accounts |
get_transactions | A batch of payment transactions over a number of days, or for an order |
get_gift_cards | The Gift Card balance, with a batch of its activity over a number of days |
get_prime_payments | Prime membership fee charges, each with its order number |
check_session | Whether you're signed in, on each Amazon site you have a session for |
get_config | The settings your assistant can change, and their values |
update_config | Changes one of those settings |
Order history and transactions come back in batches of limit results (25 by default, and a batch can run up to a
page over), with a cursor your assistant passes back to get the next batch.
Every tool that reads Amazon takes an optional site, like amazon.de, so your assistant can read each Amazon site
you shop on from one server, e.g. "my last amazon.de orders". Without it, tools read your default site, the domain
setting. Each site has its own sign-in, so ask your assistant to sign you in to each one.
Configuration
Ask your assistant to change a setting, such as the default Amazon site (e.g. amazon.co.uk) or the browser to sign in
with. Settings are shared with the amazon-orders CLI, so it follows the same changes. See
Supported Sites for the sites
amazon-orders can read.
Documentation
For more on the data the server returns, amazon-orders's official documentation is available
at Read the Docs, including the
Order entity's fields
and troubleshooting.
Contributing
Want to contribute financially? If you've found amazon-orders-mcp
useful, sponsorship would
be greatly appreciated!
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.