Defined capabilities
The assistant calls named tools for catalog, listings, inventory, orders, pricing, account health and Sponsored Products, depending on the granted scopes.
Vendooly sits between an AI assistant and the Amazon APIs you authorize. It exposes defined tools for Seller Central and Amazon Ads, keeps each request scoped to the right seller account and marketplace, and waits for explicit approval before writes.
An AI model can explain Amazon concepts on its own. Operational work needs fresh, authorized data and a clear boundary around what may be read or changed.
The assistant calls named tools for catalog, listings, inventory, orders, pricing, account health and Sponsored Products, depending on the granted scopes.
Requests stay attached to the selected org, seller account and marketplace. Agencies can work across authorized contexts without combining them.
Read operations and proposed changes are different jobs. Listing, feed, price, bid, budget and campaign writes require a visible confirmation.
The seller authorizes the relevant Seller API or Ads API scopes. Vendooly does not ask the operator to paste Amazon credentials into an AI conversation.
The MCP tool validates the org, seller account, marketplace and parameters before retrieving or preparing data.
For a write, the proposed scope remains visible and nothing is executed until the user confirms.
Each page explains the required evidence, control boundary and practical questions for one high-intent use case.
Sign up to Vendooly and authorize your seller account, and your Amazon Ads account if you want, through Amazon's official OAuth. No password in the chat, no developer registration.
Add Vendooly as a connector in Claude or ChatGPT (endpoint https://mcp.vendooly.com/mcp) and ask in plain English. The AI reads your real data, marketplace by marketplace.
Prices, stock, listings, bids, budgets and campaign state: the AI prepares the change, shows you before→after and runs it only after your explicit OK.
A server that speaks the Model Context Protocol, the open standard AI assistants use to call external tools. An Amazon seller MCP server exposes named tools (read orders, check the Buy Box, update a bid) on top of Amazon's Selling Partner API and Advertising API, so ChatGPT or Claude work on your real seller data instead of guessing.
With Vendooly: sign up, authorize your seller account and, if you want, Amazon Ads through Amazon's official OAuth, then add https://mcp.vendooly.com/mcp as a connector in Claude or ChatGPT. You ask in plain language; every write waits for your approval.
Amazon has two related tools: the Amazon Ads MCP Server, in open beta since 2 February 2026, for advertising only and requiring Amazon Ads API credentials; and the Amazon Selling Partner plugin for Amazon Quick and Claude, announced on 23 September 2026 in beta for U.S. stores only. Vendooly uses neither: it calls the official APIs directly and combines Seller Central and Ads in one connection, in Europe too.
106 tools: 65 for reading and 41 for actions. 44 are dedicated to Amazon Ads (Sponsored Products, Brands and Display) and 7 to Vendor Central. Every action tool shows a before→after preview and waits for explicit confirmation.
Start with a bounded question about listings, stock, pricing or Sponsored Products, then inspect exactly what the tool used.