amazon-seller-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGENTXRAY_TOKEN | No | Optional AgentXray API token (e.g. axr_...) used to enable live data tools from the hosted AgentXray service. Without a token, the server makes no network requests. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Settlement tools read Amazon settlement reports from this computer and return exact amounts with a 'basis' and 'gaps'; repeat the gaps and never fill one with an estimate.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| prompts | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| read_settlement_reportA | Reads an Amazon settlement report (the tab-separated flat file from Seller Central → Payments → Reports Repository) from this computer and returns what Amazon actually settled: sales, refunds, promotions, referral and FBA fees, storage, subscription, reimbursements and the net, plus units, orders, average price, FBA fee per unit and referral rate. With a unit cost it also returns profit after product cost. Amounts are exact to the cent. The file never leaves this machine. |
| settlement_profit_by_skuA | Groups the lines of an Amazon settlement report by SKU and returns, for each SKU, units, orders, sales, fees by bucket, net and net per unit. Lines Amazon booked without a SKU (storage, subscription, most reimbursements) are kept as their own unattributed group instead of being spread across products, so the SKU nets plus that group equal the report's net exactly. Set include_lines to see the individual lines behind one SKU. |
| list_settlement_reportsA | Lists the Amazon settlement reports in a folder on this computer (for example your Downloads folder), with settlement id, period, deposit date, currency and deposit total for each, newest period first. Files that are not settlement reports are skipped. |
| agentxray_live_setupA | Explains how to add live Amazon data (orders, ads, stock, account health) to this server by connecting an AgentXray account. Listed only while no AGENTXRAY_TOKEN is set; the settlement tools do not need it. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: listing local settlement files, reading one report's totals, grouping one report by SKU, and explaining live-data onboarding. The two report-reading tools are differentiated by whole-report summary versus per-SKU breakdown.
All names use snake_case, but the conventions are mixed: list_settlement_reports and read_settlement_report use verb_noun, while settlement_profit_by_sku and agentxray_live_setup are noun-phrase style. Still readable, but not a predictable pattern across the set.
Four tools are well-scoped for a settlement-report-focused server: one listing tool, two analysis tools, and one conditional onboarding helper. The count is small but each tool has a clear role.
The core settlement workflow is covered: discover local files, read totals, and break down profit by SKU. Minor gaps exist around multi-report comparison or date filtering, and the live-data option is only described rather than implemented as query tools.