How do I get my API Key and Secret?

You must contact your Liftoff (Vungle) Account Manager to receive your specialized Reporting API credentials.

What is the difference between Reporting v1 and v2?

Reporting v1 is asynchronous and used for large, detailed historical datasets. Reporting v2 is synchronous and provides quick access to spend and install metrics.

Can I filter data by country?

Yes, by including 'country' in the `dimensions` parameter of the spend report, or by configuring the group_by settings in a v1 report request.

Liftoff MCP Server for Pydantic AI 7 tools — connect in under 2 minutes

Name: Liftoff
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 7 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Liftoff through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Liftoff "
            "(7 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Liftoff?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Liftoff MCP Server

Connect your Liftoff (formerly Vungle) advertising account to any AI agent to automate your mobile marketing analytics and reporting. This MCP server enables your agent to list campaigns, request detailed performance reports, and monitor spend in real-time directly from natural language interfaces.

Pydantic AI validates every Liftoff tool response against typed schemas, catching data inconsistencies at build time. Connect 7 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Campaign Oversight — List all apps, campaigns, and creative assets to map performance IDs to readable names
Automated Reporting — Request asynchronous performance reports (v1) for deep dives into historical data
Real-time Spend — Query synchronous spend and install metrics (v2) for immediate operational awareness
Lifecycle Tracking — Monitor the status of report generation and download completed results effortlessly
Dimension Filtering — Filter your data by app, campaign, country, and platform to identify growth opportunities

The Liftoff MCP Server exposes 7 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Liftoff to Pydantic AI via MCP

Follow these steps to integrate the Liftoff MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 7 tools from Liftoff with type-safe schemas

Why Use Pydantic AI with the Liftoff MCP Server

Pydantic AI provides unique advantages when paired with Liftoff through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Liftoff integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Liftoff connection logic from agent behavior for testable, maintainable code

Liftoff + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Liftoff MCP Server delivers measurable value.

Type-safe data pipelines: query Liftoff with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Liftoff tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Liftoff and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Liftoff responses and write comprehensive agent tests

Liftoff MCP Tools for Pydantic AI (7)

These 7 tools become available when you connect Liftoff to Pydantic AI via MCP:

download_report_results

Retrieve the data for a completed report

get_report_status

Check the status of a requested report

get_spend_metrics

Get a synchronous spend and performance report (v2)

list_liftoff_apps

List all applications in your Liftoff account

list_liftoff_campaigns

List all advertising campaigns

list_liftoff_creatives

List all creative assets

request_performance_report

Requires start and end dates. Initialize a performance report request (v1)

Example Prompts for Liftoff in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Liftoff immediately.

"List all active advertising campaigns in Liftoff."

"Show recent spend and installs for campaign ID 'camp-123'."

"Request a performance report for the month of July in JSON format."

Troubleshooting Liftoff MCP Server with Pydantic AI

Common issues when connecting Liftoff to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Liftoff + Pydantic AI FAQ

Common questions about integrating Liftoff MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Liftoff MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.