How to Use the Airship MCP in Mastra AI

Q: How do I add the Airship server to a Mastra AI agent?

Instantiate the MCPClient with your Vinkius URL, then spread the output of listTools() into your Mastra AI agent configuration. This gives the agent direct access to all push and segment tools.

Q: Can Mastra AI handle human approval before sending a bulk Airship push?

Yes, you can set requireToolApproval on the agent. This pauses the workflow before the push tool executes, allowing a manager to review the push payload.

Run complex Airship push workflows and manage user segmentation with Mastra AI conditional agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Airship MCP to Mastra AI

Create your Vinkius account to connect Airship 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 Airship with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build resilient push notification workflows in Mastra AI

The `send_push_notification` tool executes mobile alerts within your Mastra AI workflow engine. If a push delivery fails due to rate limits, the framework automatically triggers exponential backoffs to guarantee the message lands. You can program conditional branches that check delivery success. If the push fails, the workflow redirects the task to alternative messaging channels or alerts your engineering team.

Automated segment cleanup using the Mastra AI engine

The `list_segments` and `list_tags` tools fetch your current audience parameters to evaluate user targeting. Mastra AI agents use this data to run scheduled maintenance steps, pruning dead channels without human intervention. This setup runs natively on your server or cloud provider. The agent identifies outdated tags, modifies list criteria, and updates your marketing lists based on real-time database changes using the Vinkius MCP Server.

Conditional user mapping via Mastra AI workflows

The `associate_named_user` tool binds device channels to specific user IDs during backend sync events. Mastra AI manages this mapping through multi-step pipelines, ensuring a device is only linked after verifying its status. By calling `get_channel_details` first, the agent checks if the channel is active. If the channel is dead, the workflow branches to skip association, preventing database clutter and wasted API calls over the MCP connection.

Setup guide

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

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

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

Instantiate the `MCPClient` with your Vinkius URL, then spread the output of `listTools()` into your Mastra AI agent configuration. This gives the agent direct access to all push and segment tools.

Yes, you can set `requireToolApproval` on the agent. This pauses the workflow before the push tool executes, allowing a manager to review the push payload.

The Mastra AI workflow engine handles retries natively. When the MCP server returns a rate limit code, the workflow pauses and retries the tool call using exponential backoff.

Yes, you can write transitions that evaluate the output of the segment details tool before deciding whether to dispatch a notification to that specific audience.

The Vinkius MCP Server runs in an ephemeral, zero-trust sandbox. Your Mastra AI code receives segment details over an encrypted SSE connection, and no audience data is stored permanently on Vinkius.

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