How to Use the Liftoff MCP in AutoGen

Q: How do I register the Liftoff MCP Server with my AutoGen agents?

Install autogen-extmcp and use mcpservertools with your Vinkius HTTP URL. Pass the resulting tool list directly into your AssistantAgent constructor to give your agents access.

Q: Can AutoGen agents run Liftoff reports asynchronously?

Yes, one AutoGen agent can request a report using requestperformancereport while another agent polls getreportstatus. The conversation structure allows them to pass control back and forth until the data is ready.

Deploy AutoGen agents to debate and optimize your Liftoff mobile ad spend.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Liftoff MCP to AutoGen

Create your Vinkius account to connect Liftoff 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 Liftoff with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate ad performance using AutoGen and Liftoff

The `get_spend_metrics` tool feeds synchronous spend data into your AutoGen multi-agent system, allowing different agents to analyze the numbers from competing angles. In your AutoGen group chat, a performance agent might push to scale Liftoff budget based on low cost-per-install, while a finance agent challenges the ROI. These AutoGen agents debate the metrics in a structured conversation loop, ensuring you don't make rash Liftoff budget changes. They use the real-time Liftoff spend data to reach a consensus before recommending any AutoGen action.

Coordinate multi-agent Liftoff reporting pipelines

The `request_performance_report` tool is triggered by a coordinator agent in AutoGen, which then delegates status monitoring to a dedicated polling agent. This polling agent calls `get_report_status` at set intervals without blocking the AutoGen coordinator from executing other Liftoff tasks. Once the Liftoff report is ready, the polling agent alerts an AutoGen data-analyst agent to run `download_report_results` and parse the CSV. This AutoGen multi-agent division of labor makes handling asynchronous Liftoff reports highly efficient.

Audit creative asset distribution with an MCP Server agent

The `list_liftoff_creatives` tool allows an asset-auditing agent in AutoGen to inspect your creative inventory. This agent compares the active Liftoff creatives against the app list retrieved by `list_liftoff_apps` to find apps missing fresh visual assets in AutoGen. The auditing agent then drafts a summary of missing Liftoff creatives and presents it to your AutoGen design coordinator agent. Using this MCP Server setup, your AutoGen agents handle Liftoff inventory checks autonomously, flagging gaps in your ad coverage.

Setup guide

Set up Liftoff 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 Liftoff 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="Liftoff_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install `autogen-ext[mcp]` and use `mcp_server_tools` with your Vinkius HTTP URL. Pass the resulting tool list directly into your `AssistantAgent` constructor to give your agents access.

Yes, one AutoGen agent can request a report using `request_performance_report` while another agent polls `get_report_status`. The conversation structure allows them to pass control back and forth until the data is ready.

Agents share data by printing tool outputs, like the JSON from `list_liftoff_campaigns`, directly into the group chat history. All active agents in the conversation can read this history to inform their next decisions.

Yes, AutoGen's MCP adapter natively supports Streamable HTTP transports. You connect your agents to your hosted Vinkius endpoint, and the adapter handles the tool schema conversion automatically.

Your Liftoff creative asset lists and performance reports are processed entirely within your local AutoGen runtime. Vinkius provides an isolated, zero-trust connection that passes the data directly to your agents without exposing your campaign strategy to external servers.

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