How to Use the Amazon DSP MCP in Mastra AI

Q: How do I integrate Amazon DSP with Mastra AI?

Add the Vinkius URL to your MCPClient servers object. Mastra auto-detects the Streamable HTTP transport and maps the DSP endpoints directly to your agent.

Q: Can Mastra AI handle Amazon DSP rate limits automatically?

Yes. The workflow engine uses built-in retries. If requestreport fails due to API throttling, Mastra waits and attempts the call again based on your specific backoff settings.

Q: How do I require human approval for Amazon DSP actions in Mastra AI?

Set the requireToolApproval flag in your agent configuration. When the system tries to fetch getcampaigndetails, it pauses execution until an admin clicks approve.

Q: Does this setup support conditional logic for ad campaigns?

Yes. You route workflows based on the output of listcampaigns. If no active campaigns exist, the workflow alerts a manager instead of trying to pull reports.

Build resilient Amazon DSP workflows with Mastra AI and handle ad ops failures automatically.

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 Mastra AI

Create your Vinkius account to connect Amazon DSP 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 DSP with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Ad Ops Workflows

This Amazon DSP MCP server wraps your programmatic ad operations in Mastra's durable workflow engine. You set up a sequence that triggers `request_report` every morning at exactly 8 AM. If the exchange throws a 503 error, Mastra catches it. The framework applies exponential backoff and tries again before pinging `get_report_status`. Your media team gets their performance numbers without someone manually clicking refresh.

Smart Campaign Routing

Media buyers require logic over raw data dumps. You build a branching workflow that checks active spend. The agent pulls data using `get_campaign_details` and evaluates the current budget pacing against your targets. Based on that output, the system branches. If pacing is slow, it triggers `list_ad_groups` to find underperforming line items. If pacing is on track, it simply logs the status and exits. You dictate the exact path the agent takes.

Mastra AI MCP Server Setup

Installation requires exactly one command. Install the latest `@mastra/mcp` package and instantiate `new MCPClient`. Point it at your Vinkius URL and spread the results from `listTools()` directly into your agent's configuration. For sensitive operations, you restrict AI autonomy. Enable `requireToolApproval` on tools like `list_audiences` or `list_creatives`. A human reviews the target segments before the workflow proceeds, keeping your ad spend strictly controlled.

Setup guide

Set up Amazon DSP 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 DSP 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-dsp-mcp-client",
  servers: {
    "amazon-dsp-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Amazon DSP 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 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 Mastra AI

Add the Vinkius URL to your `MCPClient` servers object. Mastra auto-detects the Streamable HTTP transport and maps the DSP endpoints directly to your agent.

Yes. The workflow engine uses built-in retries. If `request_report` fails due to API throttling, Mastra waits and attempts the call again based on your specific backoff settings.

Set the `requireToolApproval` flag in your agent configuration. When the system tries to fetch `get_campaign_details`, it pauses execution until an admin clicks approve.

Yes. You route workflows based on the output of `list_campaigns`. If no active campaigns exist, the workflow alerts a manager instead of trying to pull reports.

Your workflow connects through a zero-trust, ephemeral sandbox. Vinkius processes your ad group IDs and campaign budgets in memory and destroys the environment immediately after the run.

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