How to Use the Criteo Marketing API MCP in AutoGen

Let your AutoGen agents debate and optimize Criteo campaigns using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Criteo Marketing API MCP to AutoGen

Create your Vinkius account to connect Criteo Marketing API 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 Criteo Marketing API with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Set up AutoGen agent debates over Criteo budgets

This MCP Server provides the tools your AutoGen agents need to manage spend, allowing a finance agent to check `list_marketing_budgets` while a growth agent pulls `get_marketing_statistics`. One agent shouldn't have absolute power over your spend. They debate the optimal allocation in a structured AutoGen conversation. They only execute a budget change once both agree on the projected return.

Automate creative audits with AutoGen agents

This MCP Server lets specialized AutoGen agents audit your creative assets using `list_ad_creatives` and `get_ad_set_details`. Let specialized agents audit your creative assets. A compliance agent can scan metadata while a performance agent checks where they are deployed. This collaborative check ensures that no outdated or non-compliant banners stay active.

Coordinate audience targeting across AutoGen teams

This MCP Server coordinates audience targeting across AutoGen teams by exposing `list_audiences`, `list_audience_segments`, and `list_marketing_campaigns`. Managing complex ad groups requires careful coordination. An audience specialist agent can map out your current reach and share these insights with a campaign builder agent. This ensures your active groups target the correct segments.

Setup guide

Set up Criteo Marketing API 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 Criteo Marketing API 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="Criteo Marketing API_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Criteo Marketing API 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="Criteo Marketing API_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Criteo Marketing API 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 Criteo Marketing. 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 Criteo Marketing API 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 Criteo Marketing API MCP in AutoGen

You use the AutoGen MCP tool adapter to convert the server tools. Then, you pass that tool list directly into your AssistantAgent constructor.

Yes, the MCP server handles concurrent requests. Your finance agent and performance agent can query budgets and statistics at the same time without conflicts.

The AutoGen MCP adapter automatically maps the server tool schemas to the format AutoGen expects. This ensures your agents pass valid parameters to every API call.

Yes, the adapter supports both stdio and HTTP transports. For production multi-agent setups, the HTTP transport is usually the easiest to manage.

Yes. All agent communication and tool execution occur within isolated environments. Your performance metrics and advertiser configurations are never leaked or used to train public models.

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