How to Use the Amazon DSP MCP in OpenAI Agents SDK

Q: How do I connect Amazon DSP to my OpenAI Agents SDK pipeline?

Install the package using pip install openai-agents and point the HTTP endpoint to your managed MCP Server. Pass this server instance in the mcpservers list when instantiating your agent.

Q: Can I use multiple specialized agents for Amazon DSP tasks?

Yes, you can dedicate one agent to pull creatives using listcreatives and another to monitor campaigns via listcampaigns, passing context between them using SDK handoffs.

Run safe, production-grade Amazon DSP campaign automation using OpenAI Agents SDK with real-time guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Amazon DSP to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automating Campaign Audits with OpenAI Agents SDK

Your agent uses `list_campaigns` via the Amazon DSP MCP Server to scan active Amazon DSP inventory, so you don't have to manually inspect each setup. By feeding this raw metadata directly into your OpenAI Agents SDK workflow, the agent detects anomalies without human intervention. Once it's spotted an issue, the agent calls `get_campaign_details` to pull specific targeting parameters. The SDK's built-in guardrails ensure the agent never modifies budget thresholds or targeting rules without explicit approval.

Pulling Performance Reports with this MCP Server

This MCP Server lets your agent trigger `request_report` to generate custom performance metrics directly from the Amazon DSP. You don't have to poll the API manually; the agent uses `get_report_status` to check progress until the file is ready. The OpenAI tracing dashboard tracks these tool calls step-by-step, showing you exactly when the data was requested and received. You get clean, validated report data passed straight to your downstream analysis agents.

Audience and Creative Discovery

The agent executes `list_audiences` to map out your available targeting segments across different ad accounts. It matches these segments against your current creative assets fetched via `list_creatives` to find gaps in your ad coverage. Because the OpenAI Agents SDK supports direct agent handoffs, a discovery agent can pass this structured audience data to a creative optimization agent. You end up with a highly coordinated workflow that keeps your Amazon DSP targeting in lockstep with your creative inventory.

Setup guide

Set up Amazon DSP MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Amazon DSP tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Amazon DSP tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Amazon DSP tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Amazon DSP Agent",
            instructions="You have access to Amazon DSP tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the package using `pip install openai-agents` and point the HTTP endpoint to your managed MCP Server. Pass this server instance in the `mcp_servers` list when instantiating your agent.

Yes, the SDK manages execution flow, but you should configure retry logic around tools like `request_report` to handle API throttling. The agent will poll `get_report_status` until the data is ready, respecting your defined safety guardrails.

The SDK uses built-in guardrails to inspect tool arguments before they execute on the Amazon DSP API. If an agent tries to pass invalid parameters to `list_ad_groups`, the SDK blocks the call and requests correction.

Yes, you can dedicate one agent to pull creatives using `list_creatives` and another to monitor campaigns via `list_campaigns`, passing context between them using SDK handoffs.

Your campaign metadata, creative assets, and performance reports are processed in a secure, ephemeral V8 isolate sandbox. Vinkius handles the MCP authentication tokens directly, so your OpenAI Agents SDK never exposes sensitive DSP credentials to the LLM.

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