How to Use the Liftoff MCP in Mastra AI

Q: How do I handle Liftoff report failures in Mastra AI?

Mastra AI handles retries natively. Wrap your requestperformancereport call in a workflow step with a defined retry policy for when the API returns a 5xx error.

Q: Does Mastra AI support human-in-the-loop for Liftoff?

Absolutely. Use requireToolApproval on tools like campaign modifications to ensure an operator reviews the changes before they hit the Liftoff API.

Q: Can I chain multiple Liftoff tools in a Mastra AI workflow?

Yes. You can pass the output of listliftoffcampaigns directly into a loop that requests reports for each ID using requestperformancereport.

Q: How do Mastra AI and Liftoff manage large reports?

Large datasets are handled via the downloadreportresults tool. It provides a direct link to the CSV result, keeping your agent memory usage low.

Automate your ad workflows in Mastra AI with precise control over Liftoff reporting and campaign management.

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 Mastra AI

Create your Vinkius account to connect Liftoff to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Conditional workflows for Liftoff in Mastra AI

Build agents that react to performance dips automatically. Use `get_spend_metrics` as a trigger in your Mastra AI workflow to evaluate ROI and trigger logic branches based on your specific spend thresholds. If the data shows a campaign is failing, your agent can pause it or alert a team member. It turns raw numbers into actionable steps without human intervention.

Automated reporting pipelines with Mastra AI

Schedule your reporting tasks to run at specific intervals. Your Mastra AI agent can call `request_performance_report` and poll `get_report_status` in a loop until the data is ready for download. This setup handles the wait time for you. Once the file is ready, the agent pipes the output to your database or storage bucket automatically.

Agent-driven campaign inventory

Keep your local records in sync with your live ad account. By polling `list_liftoff_campaigns` and `list_liftoff_apps`, your Mastra AI agents can maintain a local index of every active asset. This is critical for long-running processes that need to cross-reference performance data against campaign metadata. You no longer have to manually verify which campaign IDs are currently active.

Setup guide

Set up Liftoff MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Liftoff tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "liftoff-mcp-client",
  servers: {
    "liftoff-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Liftoff Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Liftoff tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Liftoff transactions"
);
console.log(result.text);

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 Mastra AI

Mastra AI handles retries natively. Wrap your `request_performance_report` call in a workflow step with a defined retry policy for when the API returns a 5xx error.

Absolutely. Use `requireToolApproval` on tools like campaign modifications to ensure an operator reviews the changes before they hit the Liftoff API.

Yes. You can pass the output of `list_liftoff_campaigns` directly into a loop that requests reports for each ID using `request_performance_report`.

The server uses a zero-trust architecture. Only the specific agent instance you authorize can access your Liftoff data, and nothing is cached by the host.

Large datasets are handled via the `download_report_results` tool. It provides a direct link to the CSV result, keeping your agent memory usage low.

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