How to Use the Liftoff MCP in OpenAI Agents SDK

Q: How do I initialize the Liftoff MCP Server with the OpenAI Agents SDK?

Install the package using pip, then instantiate MCPServerStreamableHttp to connect to the MCP endpoint on Vinkius. Pass this server instance directly to the Agent constructor inside an async context manager. Set the tool caching parameter to true to avoid redundant network roundtrips.

Deploy production-grade OpenAI Agents SDK setups that pull real-time mobile ad metrics directly from Liftoff.

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 OpenAI Agents SDK

Create your Vinkius account to connect Liftoff 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 Liftoff with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run asynchronous report pipelines without timeouts

The `request_performance_report` tool initiates asynchronous mobile ad performance queries directly from your Python agent. This setup prevents your production system from hanging while waiting for heavy data payloads to compile on the server side. Your agent triggers the request, gets a report ID, and hands off the polling task to a background worker. Polling occurs via `get_report_status` to track when the data is ready for consumption. Once finished, the agent invokes `download_report_results` to write the performance metrics directly into your database.

Audit creative assets using OpenAI Agents SDK

The `list_liftoff_creatives` tool pulls active ad assets and their metadata directly into your agent's execution context. This allows your system to match creative performance against active campaigns without relying on manual CSV exports. Your agent uses `list_liftoff_apps` to map these creatives to specific mobile applications. Because the OpenAI Agents SDK supports strict runtime tracing, you can audit exactly how your agent evaluates and pairs these assets.

Track campaign spend with built-in safety

The `get_spend_metrics` tool returns synchronous spend and performance data for immediate budget evaluation. This tool gives your agent instant visibility into active budgets without waiting for long asynchronous report generation pipelines. Using this MCP Server within the OpenAI framework allows you to configure runtime guardrails. These guardrails prevent your agent from executing unauthorized budget reallocations based on the spend metrics it reads.

Setup guide

Set up Liftoff 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 Liftoff tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Liftoff 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="Liftoff Agent",
            instructions="You have access to Liftoff 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 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 OpenAI Agents SDK

Install the package using pip, then instantiate `MCPServerStreamableHttp` to connect to the MCP endpoint on Vinkius. Pass this server instance directly to the Agent constructor inside an async context manager. Set the tool caching parameter to true to avoid redundant network roundtrips.

Yes, by using the asynchronous tools provided in the server. Your agent initiates the request and polls until the status is complete, then streams the raw data. This approach keeps your production agent responsive and avoids memory spikes.

The SDK automatically inspects the Vinkius MCP endpoint and registers all seven available tools. Your agent immediately knows how to call functions like `list_liftoff_campaigns` without manual schema definition.

You manage access via the single Vinkius endpoint token associated with your account configuration. The server routes all requests to the designated account automatically, keeping your code clean.

Vinkius runs this integration inside an ephemeral V8 Isolate Sandbox with zero-trust network policies. Your advertising spend, campaign performance, and creative metadata never persist on the host system. All transit occurs over encrypted channels directly to the API endpoints.

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