How to Use the AirOps MCP in Mastra AI

Q: How does my Mastra AI agent execute an AirOps workflow and wait for it?

Use the executeworkflowsync tool for tasks where your agent needs to block and wait for the result. For anything else, executeworkflowasync is better. It returns an ID so your agent can check on it later without blocking.

Q: Can a Mastra AI agent stop a running AirOps workflow?

Yes, the cancelexecution tool is designed for this. Your agent can use its own logic—like a timeout or an external signal—to decide when to stop a process that's running on AirOps.

Q: How do I add AirOps MCP tools to my Mastra AI agent?

After creating your MCPClient with the Vinkius URL, call mcpClient.listTools(). Then, just spread the resulting tool list into the tools array when you define your agent. Mastra handles the rest.

Build resilient, multi-step AI agents. Connect Mastra AI to AirOps to orchestrate complex workflows that can handle failure and retry.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AirOps MCP to Mastra AI

Create your Vinkius account to connect AirOps 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 AirOps with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Orchestrate Failure-Proof Workflows

Mastra's strength is building robust agents, and these tools are a perfect fit. You can `execute_workflow_async` and then periodically `get_execution_status` inside a conditional loop. If a step fails, your Mastra agent can decide whether to retry or `cancel_execution`. This gives you fine-grained control over long-running processes. Instead of just hoping a workflow succeeds, you build an agent that actively manages it, handling errors with the logic you define in your Mastra code.

A Backend Agent with Long-Term Memory

Your Mastra agent can now manage its own knowledge base inside AirOps. Use the `upload_file` and `add_memory_document` tools to feed it new information from external sources. This context persists across agent runs. When the agent needs to act on that knowledge, `search_memory_store` lets it query the vector DB. This is how you build agents that don't just execute tasks, but also learn and reference past data to make better decisions.

Your Mastra AI MCP Server Control Plane

Go beyond just running workflows. Your agent can use `list_apps` to discover what capabilities are available in AirOps and `get_app_details` to inspect their configuration. This lets you build meta-agents that can provision or reconfigure other agents. You could even use `chat_with_agent` to have your Mastra agent delegate specific tasks to a specialized AirOps agent, creating a hierarchy of control.

Setup guide

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

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

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

Use the `execute_workflow_sync` tool for tasks where your agent needs to block and wait for the result. For anything else, `execute_workflow_async` is better. It returns an ID so your agent can check on it later without blocking.

Yes, the `cancel_execution` tool is designed for this. Your agent can use its own logic—like a timeout or an external signal—to decide when to stop a process that's running on AirOps.

After creating your MCPClient with the Vinkius URL, call `mcpClient.listTools()`. Then, just spread the resulting tool list into the `tools` array when you define your agent. Mastra handles the rest.

It allows your Mastra agent to delegate. Instead of doing everything itself, it can have a conversation with a specialized agent inside AirOps to get a task done. It's a way to compose agent capabilities.

Your agent will be passing workflow parameters and execution IDs to AirOps. If you use the memory tools, it will also process the raw text of any documents or files you submit via `upload_file`. Each request is handled within a zero-trust, ephemeral sandbox managed by Vinkius to keep your data contained.

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