How to Use the AirOps MCP in OpenAI Agents SDK

Q: How do I get started with AirOps and the OpenAI Agents SDK?

Install the SDK and point the MCPServerStreamableHttp client to your Vinkius MCP endpoint. The agent auto-discovers all the AirOps tools. We recommend setting cacheToolsList=True for better performance after the first run.

Q: Can my agent choose between sync and async execution with AirOps and the OpenAI Agents SDK?

Yes. Your agent gets both executeworkflowsync and executeworkflowasync as distinct tools. You can then write logic that lets the agent decide which one to call based on how quickly it needs a result.

Q: How does my agent know if a workflow succeeded?

After calling an execution tool, your agent should use getexecutionstatus with the returned execution ID. This tool provides the current state—like 'running', 'succeeded', or 'failed'—so your agent can decide what to do next.

Build production-grade agents with AirOps workflows and the OpenAI Agents SDK. Safe, traceable, and ready to deploy.

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 OpenAI Agents SDK

Create your Vinkius account to connect AirOps to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute and Monitor AirOps Workflows

This server gives your agent tools to run complex AirOps jobs. It can kick off a long-running task with `execute_workflow_async` or get an immediate result using `execute_workflow_sync`. The agent decides which tool fits the job, giving you more flexible automation. Because things don't always go as planned, your agent needs control. It can check on any job with `get_execution_status` or stop it cold with `cancel_execution`. This is how you build reliable systems that can recover from errors, a must-have for anything running in production.

Equip Your OpenAI Agent with a Memory

Make your agent smarter by giving it a persistent memory. It can take in new information using `upload_file`, then use `add_memory_document` to add that knowledge to a vector store. Your agent stops being a stateless tool and actually starts to learn from its interactions. When it's time to act, the agent uses `search_memory_store` to find relevant context before it generates a response. This grounds its output in facts you've provided, not just its general training data. It’s the right way to build agents with deep, specific expertise.

Your MCP Server for Agent Management

Your agent isn't flying blind. The `list_apps` tool gives it a full directory of available AirOps applications. It can then use `get_app_details` to inspect what any single app does before deciding to execute it. No more guessing games. For debugging or direct intervention, your code can use `chat_with_agent`. This lets you, or another supervising agent, talk directly to a specific agent running in the AirOps environment. It’s a key piece for building complex, multi-agent systems where agents manage other agents.

Setup guide

Set up AirOps MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all AirOps tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives AirOps tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate AirOps tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="AirOps Agent",
            instructions="You have access to AirOps tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the SDK and point the `MCPServerStreamableHttp` client to your Vinkius MCP endpoint. The agent auto-discovers all the AirOps tools. We recommend setting `cacheToolsList=True` for better performance after the first run.

Yes. Your agent gets both `execute_workflow_sync` and `execute_workflow_async` as distinct tools. You can then write logic that lets the agent decide which one to call based on how quickly it needs a result.

AirOps exposes workflow execution and memory management as discrete, function-like tools. This model fits perfectly with how the OpenAI SDK works, where the agent reasons about which tool to use for a specific step. It's less of a black box.

After calling an execution tool, your agent should use `get_execution_status` with the returned execution ID. This tool provides the current state—like 'running', 'succeeded', or 'failed'—so your agent can decide what to do next.

This server processes workflow execution commands, file uploads, and memory store queries. Data you send, like the contents of files from `upload_file`, passes through our ephemeral, sandboxed environment but is never stored or logged by 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