How to Use the AdRoll MCP in Mastra AI

Q: How do I connect the AdRoll MCP Server to a Mastra AI agent?

You instantiate the MCPClient from the @mastra/mcp package using your Vinkius URL. From there, you can list the AdRoll tools and add them to your agent's configuration. It's ready to go in a few lines of code.

Q: What's a good use case for AdRoll with Mastra AI?

A perfect use case is a daily reporting agent. It can use listcampaigns and getperformancereport to gather stats, and if certain KPIs aren't met, its conditional logic can trigger an alert to your team.

Q: Can I require human approval for AdRoll actions in Mastra AI?

Yes. Mastra supports a requireToolApproval option. You can build a workflow where an agent suggests pausing a low-performing AdRoll campaign but requires a person to approve the action before it executes.

Build resilient AdRoll automation with Mastra AI. Create workflows that retry, branch, and report on campaign performance without flaky scripts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AdRoll MCP to Mastra AI

Create your Vinkius account to connect AdRoll 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 AdRoll with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Unbreakable Reporting Bots

Use Mastra's workflow engine to build a bot that pulls AdRoll data on a schedule. Your agent calls `get_performance_report` to get the numbers. Mastra handles the rest. If the AdRoll API is temporarily down or returns a rate limit error, Mastra's automatic retry with exponential backoff kicks in. You don't have to write any of that logic. Your report will run, period.

Create Smart AdRoll Workflows

This is where Mastra's conditional branching really pays off. Your agent can `list_campaigns` to get everything that's active, then run `get_performance_report` for each one. If a campaign's performance drops below a set threshold, your Mastra agent can trigger a completely different action, like sending a Slack alert or creating a Jira ticket. It's true automation that reacts to real-world data, not just a simple data fetch.

Manage All AdRoll Accounts with One Agent

Your Mastra agent can iterate through every single client account using `list_advertisables`. This is a huge time-saver for agencies that manage dozens of AdRoll advertisers. Build a workflow that pulls `get_campaign_details` for every campaign across all accounts and syncs the data to your internal database. The Mastra engine ensures the job completes, no matter how many accounts it has to process.

Setup guide

Set up AdRoll 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 AdRoll 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: "adroll-mcp-client",
  servers: {
    "adroll-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent AdRoll 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 AdRoll. 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 AdRoll 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 AdRoll MCP in Mastra AI

You instantiate the `MCPClient` from the `@mastra/mcp` package using your Vinkius URL. From there, you can list the AdRoll tools and add them to your agent's configuration. It's ready to go in a few lines of code.

Yes, that's a core feature of the Mastra AI framework. If a tool like `get_performance_report` fails because of a temporary network issue, the agent automatically retries with exponential backoff. You don't have to code for it.

A perfect use case is a daily reporting agent. It can use `list_campaigns` and `get_performance_report` to gather stats, and if certain KPIs aren't met, its conditional logic can trigger an alert to your team.

Yes. Mastra supports a `requireToolApproval` option. You can build a workflow where an agent suggests pausing a low-performing AdRoll campaign but requires a person to approve the action before it executes.

The MCP server only interacts with AdRoll's API using permissions you've set. It processes campaign metadata and performance statistics in a completely isolated sandbox. Your Vinkius token secures the connection, and no data is ever stored.

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