How to Use the Liftoff MCP in Google ADK

Q: How do I set up the Liftoff MCP Server inside a Google ADK agent?

Install the library and define an McpToolset pointing to your Vinkius MCP URL. Pass this toolset directly into the tools list of your LlmAgent configuration.

Feed clean mobile ad performance data directly into your Gemini models using the Google ADK.

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 Google ADK

Create your Vinkius account to connect Liftoff to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed campaign metadata directly into Vertex AI

The `list_liftoff_campaigns` tool retrieves your active advertising campaigns and passes them straight to your Gemini reasoning loop. This direct integration lets your agent analyze active campaign structures alongside your existing cloud-hosted business intelligence data. You use `list_liftoff_apps` to map these campaigns to specific mobile applications registered in your account. Gemini's massive context window easily holds this metadata, allowing for deep reasoning across thousands of campaign entities.

Connect BigQuery with your Google ADK MCP Server

The `get_spend_metrics` tool pulls synchronous performance and spend data directly into your enterprise data pipelines. This allows your agent to compare current mobile ad spend against historical database records in real time. By wrapping this MCP toolset in the `McpToolset` class, your Gemini agents can invoke these tools during active multi-step reasoning chains. You can filter the tools to expose only the spend metrics, keeping your enterprise agent focused on budget tasks.

Handle heavy reporting files with cloud storage

The `download_report_results` tool retrieves raw performance data from completed asynchronous reporting jobs. This tool works in tandem with the asynchronous generation pipeline to prevent your agent from hitting payload limits. Your agent triggers the report via `request_performance_report` and monitors the progress using `get_report_status`. Once the status resolves, the agent downloads the CSV payload and writes it directly to Google Cloud Storage.

Setup guide

Set up Liftoff MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Liftoff tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Liftoff_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Liftoff tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install the library and define an `McpToolset` pointing to your Vinkius MCP URL. Pass this toolset directly into the tools list of your `LlmAgent` configuration.

Trigger the report asynchronously to avoid blocking your Gemini execution thread. Use the status checking tool to poll for completion before attempting to download the final CSV payload.

Yes, you can pass a list of allowed tool names to your toolset configuration. This prevents your agent from accessing administrative functions when it only needs to read spend metrics.

Gemini models can ingest entire creative lists retrieved by the assets tool. This lets the model evaluate performance trends across all your active assets in a single reasoning pass.

Vinkius runs the server inside an isolated V8 sandbox with strict zero-trust network rules. No advertising spend, campaign performance, or creative metadata is cached or stored outside your designated cloud environment.

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