How to Use the Amazon Ads MCP in Vercel AI SDK

Q: How do I handle authentication for Amazon Ads when using Vercel AI SDK?

You pass your Vinkius credentials through the authProvider configuration when initializing the client. This keeps your Amazon advertiser tokens secure on the server side while your Next.js frontend handles user interactions.

Q: Can I stream Amazon Ads report status updates in real-time with Vercel AI SDK?

Yes. By combining requestspreport and getreportstatus with streamText, the SDK streams the status of your Sponsored Products reports directly to your React components as they compile on Amazon's servers.

Q: Do I need to write custom API endpoints to fetch Amazon Ads campaigns in Vercel AI SDK?

No. You initialize the client using createMCPClient and pass mcpClient.tools() directly to the SDK's generation functions to query listspcampaigns and listsbcampaigns out of the box.

Q: How do I close connection resources after fetching my ad groups?

Always call mcpClient.close() in your execution block. This teardown step ensures your serverless functions terminate cleanly after fetching data from the MCP Server via listspadgroups.

Stream live Amazon Ads performance metrics and campaign structures directly into your Next.js frontend with Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amazon Ads MCP to Vercel AI SDK

Create your Vinkius account to connect Amazon Ads to Vercel AI SDK 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 Ads with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live-stream Sponsored Products data to your UI

Your React app can now render live Amazon Ads campaign data without waiting for entire payloads to resolve. By connecting the Vercel AI SDK to this MCP Server, your UI streams campaign lists via `list_sp_campaigns` and ad groups using `list_sp_ad_groups` straight to the user's screen. You don't need to write custom API endpoints to fetch Amazon's complex advertising hierarchies inside Next.js. The SDK handles the streaming transport while the server pulls the raw advertising profiles using `list_profiles`, giving your users instant feedback as your agent builds their dashboard.

Run background ad reporting on Vercel Edge Functions

Edge functions demand fast execution and low memory overhead when processing Amazon Ads performance metrics. This setup lets you initiate heavy advertising reports via `request_sp_report` and check their generation progress using `get_report_status` inside lightweight edge runtimes. Because Vinkius hosts the MCP Server execution layer, your Vercel Edge functions stay light. You call `mcpClient.tools()` to grab the tools, stream the status updates, and call `mcpClient.close()` to clean up resources before the edge timeout hits.

Build interactive Amazon Ads tools with Vercel AI SDK

Let your Next.js users modify keyword strategies on the fly using interactive Vercel AI SDK components. Your agent can call `list_sb_keywords` and `list_sp_keywords` to analyze keyword targets and suggest adjustments directly inside the chat interface. Using the SDK's tool-calling capabilities, the LLM decides which search terms need optimization. The results render as interactive React elements instead of plain text, letting sellers manage their Sponsored Brands campaigns without leaving your application.

Setup guide

Set up Amazon Ads MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Amazon Ads tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Amazon Ads transactions",
});

console.log(text);
await mcpClient.close();

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 Ads. 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 Ads 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 Ads MCP in Vercel AI SDK

You pass your Vinkius credentials through the `authProvider` configuration when initializing the client. This keeps your Amazon advertiser tokens secure on the server side while your Next.js frontend handles user interactions.

Yes. By combining `request_sp_report` and `get_report_status` with `streamText`, the SDK streams the status of your Sponsored Products reports directly to your React components as they compile on Amazon's servers.

No. You initialize the client using `createMCPClient` and pass `mcpClient.tools()` directly to the SDK's generation functions to query `list_sp_campaigns` and `list_sb_campaigns` out of the box.

Always call `mcpClient.close()` in your execution block. This teardown step ensures your serverless functions terminate cleanly after fetching data from the MCP Server via `list_sp_ad_groups`.

Your advertiser profiles, keyword targets, and campaign budgets stay inside Vinkius's isolated V8 sandbox. Data is processed ephemerally and never stored on disk, keeping your proprietary advertising metrics completely private.

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