How to Use the Amazon Selling Partner MCP in Mastra AI

Q: How do I hook up the Amazon Selling Partner MCP Server to Mastra AI?

Install @mastra/mcp@latest. Initialize it with new MCPClient({ id: "amazon", servers: { name: { url: new URL("YOURVINKIUSURL") } } }). Then call mcpClient.listTools() and spread them into your agent's tool array.

Q: How does Vinkius protect buyer PII when pulling order items?

Every listorders or getorderitems request routes through a zero-trust architecture. The Vinkius platform authenticates the endpoint token, executes the fetch, and instantly purges the buyer names and addresses from memory. We hold no persistent data.

Build resilient Amazon workflows with Mastra AI. Handle rate limits, retry failed syncs, and branch logic based on FBA stock levels.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amazon Selling Partner MCP to Mastra AI

Create your Vinkius account to connect Amazon Selling Partner to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Amazon Selling Partner with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Conditional FBA Restock Logic

Checking Amazon inventory manually leads to API throttling. Mastra AI fixes that by wrapping this MCP Server in a workflow engine with exponential backoff. You configure an agent to run `list_fba_inventory` every morning without worrying about breaking the script. If stock drops below 50 units, the workflow branches. The agent hits `search_catalog` to verify the current buy box price, then triggers an approval request. Mastra's `requireToolApproval` halts execution until a human manager clicks yes to generate a new shipment.

Automated Financial Auditing

Sellers lose money when they ignore refund discrepancies in their financial events. Set up a scheduled Mastra workflow to pull `list_financial_events` at the end of every billing cycle. The agent automatically audits the fees and payout amounts. If the agent spots an anomaly in the transaction data, it branches to a deeper investigation. It runs `create_report` to request the full ledger, waits, and polls `get_report_status`. If the report fails to generate, Mastra automatically retries without waking you up.

Mastra AI Order Resolution

Customer complaints require immediate context from their order history. When a ticket opens, your Mastra agent grabs the buyer details and executes `list_orders` to find the exact purchase history across all regions pulled from `list_marketplaces`. The workflow then isolates the specific transaction using `get_order_items`. If the item shipped, the agent drafts a response. If it sits in pending status, the workflow routes the ticket to a human support tier. You build complex routing logic while the MCP Server handles the Amazon data.

Setup guide

Set up Amazon Selling Partner MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Amazon Selling Partner tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "amazon-selling-partner-mcp-client",
  servers: {
    "amazon-selling-partner-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Amazon Selling Partner Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Amazon Selling Partner tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Amazon Selling Partner transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Amazon Selling Partner. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Amazon Selling Partner now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Amazon Selling Partner MCP in Mastra AI

Install `@mastra/mcp@latest`. Initialize it with `new MCPClient({ id: "amazon", servers: { name: { url: new URL("YOUR_VINKIUS_URL") } } })`. Then call `mcpClient.listTools()` and spread them into your agent's tool array.

Yes. Mastra has built-in exponential backoff. If Amazon throttles your `list_product_types` request, the workflow engine automatically waits and retries the tool call without breaking the script.

You can enforce manual checks before any tool executes. Just enable `requireToolApproval` on tools like `create_report`, and the agent pauses until an admin gives the green light.

Mastra auto-detects the transport. Since Vinkius provides a single endpoint token, the client will automatically negotiate Streamable HTTP or SSE to fetch your catalog items.

Every `list_orders` or `get_order_items` request routes through a zero-trust architecture. The Vinkius platform authenticates the endpoint token, executes the fetch, and instantly purges the buyer names and addresses from memory. We hold no persistent data.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript