How to Use the Amazon DSP MCP in AutoGen

Deploy AutoGen agent teams to debate, analyze, and optimize your Amazon DSP programmatic buys.

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 AutoGen

Create your Vinkius account to connect Amazon DSP to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent campaign analysis

Complex media buys require competing perspectives. Set up a performance agent that pulls active flights via `list_campaigns` and a compliance agent that reviews the underlying `list_ad_groups` structures. They do not just execute commands silently. The agents discuss the data over the MCP connection, flag misaligned targeting parameters, and negotiate a consensus before presenting a final optimization plan to the human buyer.

Connect this MCP Server to specialist agents

Give specific tasks to dedicated personas. An analytics agent fires off `request_report` and monitors the queue with `get_report_status`, while a strategy agent waits for the data to drop. Once the numbers come back, the strategy persona cross-references the metrics with `get_campaign_details`. The agents argue about which flights are underperforming until they agree on a recommendation.

Cross-examine audiences and creative assets

Matching the right message to the right segment is rarely straightforward. A targeting agent pulls segments using `list_audiences`, while a brand agent reviews the available catalog via `list_creatives`. The two personas debate the alignment. If the brand agent thinks a specific creative is wrong for a high-value audience, it challenges the targeting agent's assumptions right in the conversation thread.

Setup guide

Set up Amazon DSP MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Amazon DSP tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Amazon DSP_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Amazon DSP data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Amazon DSP_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Amazon DSP data")
    print(result.messages[-1].content)

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 AutoGen

Use the server tools helper with your Vinkius endpoint URL. Pass the resulting tool list directly to your assistant agent constructor.

Yes. One agent handles the asynchronous reporting loop, while another agent analyzes the final metrics and debates the findings with a human proxy.

The adapter translates everything behind the scenes. Your agents understand the required arguments for campaign lookups without any manual schema mapping.

Write it into the system prompt for your primary agent. Instruct it to challenge any other agent that makes claims without citing raw API data from the platform.

We run the MCP Server connection through a stateless sandbox. Your ad URLs and audience segment IDs exist only during transit to your local conversation environment. Vinkius retains absolutely nothing.

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