How to Use the Amazon DSP MCP in Vercel AI SDK

Q: How do I connect Amazon DSP to Vercel AI SDK?

Install the @ai-sdk/mcp package. Initialize your MCP client with createMCPClient using your Vinkius HTTP transport URL, then pass the retrieved tools into streamText.

Q: Can Vercel AI SDK stream Amazon DSP reports to my Next.js app?

Yes. When the agent triggers requestreport, the resulting data streams directly to your React components. Users watch the numbers appear as the system processes them.

Q: How do I filter which Amazon DSP MCP tools my app exposes?

You map over the array returned by mcpClient.tools(). Filter out listadgroups or listcreatives before passing the final object to your text generation function.

Stream Amazon DSP campaign data straight into your React frontends using the 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 DSP MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vercel AI SDK Streaming for Ad Data

Connect this Amazon DSP MCP server to your Next.js project to stream campaign metrics live instead of showing users a loading spinner. When a media planner asks for weekly stats, your agent hits `request_report` and immediately pushes the response chunks directly to the UI. The integration manages the polling behind the scenes. Your code calls `get_report_status` repeatedly, updating the frontend state the second the data drops. You get real-time interface updates without wiring up manual WebSockets.

Render Audiences in Real-Time

Custom media dashboards require instant access to targeting parameters. Pass the `list_audiences` and `list_creatives` tools into your `streamText` function. Your AI client grabs the exact segments and banner IDs attached to a specific advertiser account. Those results render immediately in your Svelte or Vue components. Media planners see the available creative assets populate instantly. They adjust targeting on the fly without waiting for a massive JSON payload to resolve.

Edge-Ready Campaign Inspection

Inspecting programmatic ad setups usually means navigating clunky native interfaces. Give your users a chat interface that understands their specific DSP setup. By exposing `get_campaign_details` to your edge functions, the agent pulls budget, pacing, and flight dates on demand. It digs deeper by chaining `list_ad_groups` to show exactly which line items are active right now. You keep the serverless architecture lean because Vinkius manages the actual MCP connection. Just call `mcpClient.close()` when the stream finishes.

Setup guide

Set up Amazon DSP 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 DSP 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 DSP 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 DSP. 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 DSP 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 DSP MCP in Vercel AI SDK

Install the `@ai-sdk/mcp` package. Initialize your MCP client with `createMCPClient` using your Vinkius HTTP transport URL, then pass the retrieved tools into `streamText`.

Yes. When the agent triggers `request_report`, the resulting data streams directly to your React components. Users watch the numbers appear as the system processes them.

The tool execution returns an error state within the stream. Your UI catches this through the standard `useChat` hook, letting you display a fallback message instantly.

You map over the array returned by `mcpClient.tools()`. Filter out `list_ad_groups` or `list_creatives` before passing the final object to your text generation function.

We isolate your connection in an ephemeral V8 sandbox. Vinkius only passes your audience and creative metadata between the ad exchange and your application, storing nothing permanently.

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