How to Use the AdRoll MCP in AutoGen

Q: How do I add AdRoll tools to AutoGen?

Use mcpservertools with a StreamableHttpServerParams configuration. Pass the resulting tool list directly into your AssistantAgent constructor.

Q: Does AutoGen handle the AdRoll tool schemas automatically?

The McpToolAdapter translates everything behind the scenes. Your agents know exactly what parameters the marketing tools require without manual mapping.

Bring AdRoll into your AutoGen multi-agent debates. Let specialized AI agents optimize your display campaigns together.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AdRoll MCP to AutoGen

Create your Vinkius account to connect AdRoll 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 AdRoll with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Campaign Optimization

Marketing decisions require balancing competing priorities. In AutoGen, a budget-focused agent pulls data using `get_report` while a growth agent argues for higher spend. They debate the metrics and reach a consensus before you approve any changes. You get a virtual marketing team in your terminal. One agent runs `list_campaigns` to find underperforming runs, and another reviews the structure. They challenge each other's assumptions until the best path forward emerges.

Automated Creative Audits

Stop reviewing banners by yourself. Assign the `list_ads` tool to a creative-analyst agent, and let it pull the entire inventory. A compliance agent then checks those assets against your brand guidelines. The resulting conversation uncovers issues you might miss. By combining `list_adgroups` with the ad data, the agents map out exactly which creatives are assigned where. They negotiate the required fixes and hand you a finalized punch list.

AdRoll MCP Server Audience Strategy

Defining retargeting pools is complex work. An audience-specialist agent executes `list_segments` to see who you currently track. A separate strategy agent evaluates whether those cohorts match your current sales goals. Account management happens through dialogue. The system uses `list_advertisables` and `get_campaign` to understand the broader account context. The agents discuss the setup, flag missing audiences, and agree on a revised targeting plan.

Setup guide

Set up AdRoll 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 AdRoll 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="AdRoll_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent AdRoll 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="AdRoll_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent AdRoll 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 AdRoll. 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 AdRoll 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 AdRoll MCP in AutoGen

Use `mcp_server_tools` with a `StreamableHttpServerParams` configuration. Pass the resulting tool list directly into your `AssistantAgent` constructor.

Yes. You provide the tool definitions to the agents that need them. They coordinate the execution during their conversational turns.

Single agents make mistakes. Forcing a financial agent and a marketing agent to debate the performance metrics ensures a much higher quality analysis.

The `McpToolAdapter` translates everything behind the scenes. Your agents know exactly what parameters the marketing tools require without manual mapping.

Vinkius manages the authentication layer entirely. Your agents can pull campaign budgets and return-on-ad-spend figures through an isolated environment that tears itself down the moment the API call finishes.

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