One list across every Amazon client account you manage

An agency running fifty Amazon accounts does not have a dashboard problem, it has a which-of-my-fifty-clients-needs-me-today problem, and no per-account view answers that. AgentXray reads every connected account on a schedule and returns one list ranked across the whole book, worst first, with each row naming the account it belongs to and the source its number was measured from: search-term history, inventory age, the listing's own health issues in Amazon's wording, settlement line items, and the account health tier Amazon itself reports.

Price and trial

Agency Starter is $99 a month for up to 3 connected client accounts and starts with a 14-day trial, no card to start. Larger agency plans are priced per connected client account and arranged by conversation. See agency pricing.

Every client on one screen, with what they made

The agency panel opens on the whole book: clients selling more than one product first, then single-product clients, then accounts with nothing live, and the most profitable client leads each group, over the last 7, 30 or 90 days. A product counts when Amazon shows it as buyable and has seen it this week, because Amazon's listing report keeps SKUs it dropped long ago. Profit is the same figure that client's own profit panel shows, before advertising. Currencies are never added together or converted, and a client with no sales says so instead of showing zero.

How a client joins: one link, approved on Amazon

An agency cannot connect a client's Seller Central itself; Amazon asks for the client's own login. The workspace owner makes a link and sends it, or has AgentXray email it. The client opens a page naming the agency, picks their store and approves on Amazon's own consent page, with no AgentXray account and without AgentXray ever seeing their password. The account appears in the agency's list under the name it was given. The link works once and for seven days and can be withdrawn; the client can remove access at any time in Seller Central, Apps and Services, Manage Your Apps. An Amazon account already connected to another AgentXray workspace is refused, not moved.

Your AI drafts the change; a person approves it

Your own Claude or ChatGPT connects over the Model Context Protocol, names which client it is acting for, and files a bid cut, negative keyword, budget or listing change as a draft. The draft waits in an approval queue. The connector token that wrote it cannot authenticate against the approval endpoint, so a leaked connector can propose anything and change nothing.

Your team, and the report your client reads

A viewer reads and changes nothing. An operator does the daily work: works the list, drafts changes and approves them. The owner can also connect and remove client accounts and manage the team and billing. The client report is written for the email thread you already have with that client: what was found, what was changed, and what each change did, every change with its own result and never summed into one number; a change still settling says the date it will be judged.

Naming the client is required, not optional

Twenty clients on amazon.de is twenty accounts and one marketplace. Where more than one connected account could match, the system refuses to guess and asks which client you meant. A resolver that quietly picks the oldest match is how a change drafted for one client lands on another, with Amazon accepting it and nothing reporting an error.

What we do not claim

• We are not your data warehouse. If a connector already feeds your BI, keep it; this sits on top and decides what to do about what it says.
• Client logins are not built. Your client approves access on Amazon's page and reads the report you send; a branded workspace your client signs into is not shipped.
• Profit per client is before advertising. Ad spend is not yet matched to each client's account, so it is not divided between clients by a guess.
• Nothing runs unattended. Every change is approved by a person before it reaches Amazon.

Setting up an agency workspace, step by step · Agency pricing · What the platform measures · How seller data is kept apart