How to Use the MoEngage MCP in Mastra AI

Q: How do I register the MoEngage MCP Server tools with a Mastra AI agent?

Install @mastra/mcp and instantiate the client using the Vinkius connection URL. You can then list the tools and spread them directly into your Mastra AI agent's tool configuration, granting it access to sendpush and getcustomer.

Q: How does Mastra AI use MoEngage segment data to make decisions?

The agent calls getsegment or listsegments to retrieve current audience criteria. It then uses this data inside Mastra's conditional steps to route users to the correct branch of your automated campaign.

Q: Is there a way to verify the MoEngage connection inside a Mastra AI workflow?

You can use checkmoengagestatus as an initialization step for this MCP Server. If the connection check fails, Mastra AI can trigger an alert to your engineering team before attempting any campaign actions.

Build resilient, self-healing MoEngage marketing workflows and automated push campaigns with Mastra AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MoEngage MCP to Mastra AI

Create your Vinkius account to connect MoEngage 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 MoEngage with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate MoEngage campaigns with Mastra AI workflows

Run complex marketing flows that don't break when an API hiccup occurs. By combining Mastra AI's workflow engine with this MCP Server, you can chain `upsert_customer` and `send_push` into structured, stateful steps with built-in retry logic. If a push notification fails, the workflow automatically backs off and retries, or branches to update the device state using `update_device`. You write the logic once, and Mastra handles the execution safety.

Branch your marketing logic based on live segment data

Your agent can check a user's current status using `get_segment` or `get_campaign_stats` before deciding on the next action. Mastra AI routes the execution path dynamically based on these real-time metrics. For example, if a user is not in a target segment, the agent can run `track_event` to trigger a re-engagement flow instead of sending a redundant message. This keeps your messaging targeted and prevents spamming your users.

Require approvals before sending mass MoEngage campaigns

Prevent accidental mass notifications by inserting approval steps into your Mastra AI agents. When an agent decides to run `send_push` for a large audience, Mastra pauses the execution and prompts your team for verification. Once approved, the agent continues the workflow, running `list_campaigns` or trigger tools to execute the job. It gives you complete control over autonomous marketing actions without sacrificing speed.

Setup guide

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

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

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

Install `@mastra/mcp` and instantiate the client using the Vinkius connection URL. You can then list the tools and spread them directly into your Mastra AI agent's tool configuration, granting it access to `send_push` and `get_customer`.

Yes, Mastra AI's built-in workflow engine handles rate limits by queueing tasks and retrying failed calls. When using `track_events_bulk`, the framework manages the batch sizes and backoff intervals to stay within API limits.

The agent calls `get_segment` or `list_segments` to retrieve current audience criteria. It then uses this data inside Mastra's conditional steps to route users to the correct branch of your automated campaign.

You can use `check_moengage_status` as an initialization step for this MCP Server. If the connection check fails, Mastra AI can trigger an alert to your engineering team before attempting any campaign actions.

Mastra AI processes your customer identifiers and custom event properties within isolated runtime environments. Vinkius secures the API keys, meaning your user data is only transmitted over encrypted channels to MoEngage's endpoints.

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