How to Use the Amazon Marketing Cloud MCP in Vercel AI SDK

Q: How does Vercel AI SDK handle long-running Amazon Marketing Cloud queries?

The SDK uses createexecution to start the query and polls getexecutionstatus over edge-friendly HTTP. The model streams status updates to the UI, keeping the user informed while Amazon processes the heavy SQL payload.

Q: Can I cancel an active Amazon Marketing Cloud execution from Vercel AI SDK?

Yes, the model invokes deleteexecution if a user cancels the operation in your chat UI. This stops the query immediately on Amazon's side, saving you from unnecessary AMC query costs.

Q: How do I authenticate my Amazon Marketing Cloud MCP Server inside Vercel AI SDK?

You configure the server URL in your createMCPClient transport setup. Vinkius handles the underlying Amazon Web Services credentials, so your Next.js edge route only needs a single secure endpoint token.

Q: Can the model modify existing SQL workflows?

Yes, by using updateworkflow and getworkflowdetails. The model inspects the current SQL structure, applies the requested changes, and pushes the update back to AMC.

Feed live Amazon Marketing Cloud SQL queries directly into Vercel AI SDK UI components without loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amazon Marketing Cloud MCP to Vercel AI SDK

Create your Vinkius account to connect Amazon Marketing Cloud 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 Marketing Cloud with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live AMC Query Streaming with Vercel AI SDK

This MCP Server exposes tools like `create_execution` and `get_execution_status` to let your React or Next.js app trigger AMC SQL runs and watch their progress live. Your AI client initiates the query, polls the status, and streams the changing state directly to the user's screen. Instead of making users wait for heavy SQL reports to compile in the background, the UI displays real-time execution phases. You get raw JSON chunks parsed on the fly, feeding your custom charting components the second Amazon completes the run.

Dynamic AMC Workflow Management

Managing marketing workflows happens in real-time when you pair `create_workflow` and `update_workflow` with the Vercel AI SDK. Your application lets users describe their campaign attribution models in plain English, which the SDK instantly translates into active AMC structures. The SDK handles the edge-compatible transport to update existing SQL definitions. If a user wants to tweak an attribution window, the model rewrites the workflow and shows the updated SQL block in the chat interface instantly.

Immediate SQL Data Download Generation

You can grab secure download links for completed SQL datasets using `get_execution_download_urls` directly through your Vercel AI SDK stream. This MCP Server fetches the links and hands them off to your frontend. These secure URLs stream straight into your frontend as clickable download buttons. This prevents your Edge Functions from timing out on massive Amazon Marketing Cloud payloads, as the browser handles the direct file download.

Setup guide

Set up Amazon Marketing Cloud 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 Marketing Cloud 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 Marketing Cloud 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 Marketing Cloud. 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 Marketing Cloud 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 Marketing Cloud MCP in Vercel AI SDK

The SDK uses `create_execution` to start the query and polls `get_execution_status` over edge-friendly HTTP. The model streams status updates to the UI, keeping the user informed while Amazon processes the heavy SQL payload.

Yes, the model invokes `delete_execution` if a user cancels the operation in your chat UI. This stops the query immediately on Amazon's side, saving you from unnecessary AMC query costs.

You configure the server URL in your `createMCPClient` transport setup. Vinkius handles the underlying Amazon Web Services credentials, so your Next.js edge route only needs a single secure endpoint token.

Yes, by using `update_workflow` and `get_workflow_details`. The model inspects the current SQL structure, applies the requested changes, and pushes the update back to AMC.

Yes, because the server only touches your SQL query definitions and temporary S3 download URLs. Your raw AMC event-level database records never pass through or get stored on Vinkius servers; they remain securely inside your AWS clean room.

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