How to Use the Liftoff MCP in CrewAI

Use Liftoff tools in CrewAI to build autonomous agents that pull campaign data and monitor ad spend without you lifting a finger.

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 CrewAI

Create your Vinkius account to connect Liftoff to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate campaign data extraction in CrewAI

Your agents can now pull live numbers directly from your advertising account. By calling `list_liftoff_campaigns` and `list_liftoff_apps`, your research agent identifies which assets are underperforming before the human team even notices. This setup removes the manual grunt work of logging into dashboards. Instead, your CrewAI agents iterate through your current setup and flag issues based on the raw data they pull.

Monitor performance reports as an MCP Server

The `request_performance_report` tool kicks off deep data jobs that your agents track using `get_report_status`. Once the job finishes, the agent uses `download_report_results` to bring the CSV directly into the workspace for analysis. This workflow turns your CrewAI agents into persistent analysts. They handle the polling logic and file retrieval so you don't have to manage long-running background tasks.

Real-time spend tracking for autonomous crews

Your agents get immediate feedback on budget usage by executing `get_spend_metrics`. This allows your finance agent to compare current spend against your caps in real-time, preventing overages before they happen. Because this tool is synchronous, the agent gets the numbers it needs in a single pass. It’s the fastest way to feed raw performance data into your agent’s decision-making loop.

Setup guide

Set up Liftoff MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Liftoff tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Liftoff Analyst",
    goal="Access and analyze Liftoff data via MCP.",
    backstory="Expert analyst with direct Liftoff access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Liftoff transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Liftoff Analyst",
        goal="Access and analyze Liftoff data via MCP.",
        backstory="Expert analyst with direct Liftoff access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Liftoff transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Yes, you can assign a task to a CrewAI agent that triggers the Liftoff MCP Server to request and download reports. The agent handles the status polling and file saving as part of its standard execution flow.

Your agents store the output of Liftoff tools in their shared memory. This allows one agent to fetch data and another to summarize it for your final report.

Your credentials never leave your local environment. The Liftoff MCP Server acts as a secure bridge, and CrewAI only receives the specific data points your agents request.

If a tool call fails, the agent receives an error message directly. You can program your CrewAI task to retry the request or alert you via another agent.

This server only accesses your advertising campaign metadata, spend metrics, and performance report CSVs. It does not touch PII or sensitive user-level data from your mobile apps.

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