How to Use the Zeabur (PaaS Deployment) MCP in OpenAI Agents SDK

Q: How do I check build status with Zeabur (PaaS Deployment) and OpenAI Agents SDK?

You retrieve the necessary build logs using getbuildlogs. Your agent can then read those logs to determine if the deployment succeeded or failed. Since you're building a production system with the OpenAI Agents SDK, checking these logs is a critical safety step.

Q: Can my agents deploy code with Zeabur (PaaS Deployment) and OpenAI Agents SDK?

Yes. Your agent can use deploytemplate to push out services using defined YAML specifications. Before deployment, the process requires calling createuploadstage, which handles getting all your pre-packaged application files ready for upload.

Q: How do I manage container files with Zeabur (PaaS Deployment) and OpenAI Agents SDK?

The downloadfile tool lets you grab any file directly from a running service container. You can use this to pull back configuration maps or runtime artifacts after executing commands like executecommand.

Q: Does Zeabur (PaaS Deployment) support email notifications with OpenAI Agents SDK?

It does. The server provides three tools: sendemail, scheduleemail, and sendbatchemails. Your agent just needs the correct ZEABUREMAILTOKEN to use these functions for sending alerts.

Manage deployments, containers, and messaging with your OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Zeabur (PaaS Deployment) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Zeabur (PaaS Deployment) 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 Zeabur (PaaS Deployment) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy services using YAML templates.

The `deploy_template` tool lets you roll out a service defined by a standard YAML specification. Your agent handles the full lifecycle: first, it calls `create_upload_stage` to prepare the necessary files, then uses `prepare_deployment` before finally running `deploy_template`. This workflow ensures your production application lands exactly where it should.

Run commands inside service containers.

Need to poke around a deployed service? The `execute_command` tool runs any command directly within the container runtime. You can pair this with `download_file` to pull back logs or artifacts needed for debugging. This gives your agent deep visibility into what's happening at the application level.

Send transactional and batch emails.

When a deployment finishes, you need to tell someone. Use `send_email` for single alerts or `send_batch_emails` if you're notifying dozens of users about the update. Remember that these email tools require a valid ZEABUR_EMAIL_TOKEN to actually send anything out.

Setup guide

Set up Zeabur (PaaS Deployment) 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 Zeabur (PaaS Deployment) tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Zeabur (PaaS Deployment) 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="Zeabur (PaaS Deployment) Agent",
            instructions="You have access to Zeabur (PaaS Deployment) 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 Zeabur. 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 Zeabur (PaaS Deployment) 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 Zeabur (PaaS Deployment) MCP in OpenAI Agents SDK

You retrieve the necessary build logs using `get_build_logs`. Your agent can then read those logs to determine if the deployment succeeded or failed. Since you're building a production system with the OpenAI Agents SDK, checking these logs is a critical safety step.

Yes. Your agent can use `deploy_template` to push out services using defined YAML specifications. Before deployment, the process requires calling `create_upload_stage`, which handles getting all your pre-packaged application files ready for upload.

The `download_file` tool lets you grab any file directly from a running service container. You can use this to pull back configuration maps or runtime artifacts after executing commands like `execute_command`.

It does. The server provides three tools: `send_email`, `schedule_email`, and `send_batch_emails`. Your agent just needs the correct ZEABUR_EMAIL_TOKEN to use these functions for sending alerts.

This MCP server handles deployment status and build logs. Your agent can read the output of `get_build_logs` to confirm whether an application deployment succeeded or failed.

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