How to Use the Dokku MCP in OpenAI Agents SDK

Q: How do I connect the Dokku MCP Server to the OpenAI Agents SDK?

Install openai-agents via pip and initialize the server using MCPServerStreamableHttp pointing to your Vinkius endpoint. Pass the server instance inside the mcpservers list when creating your Agent. Enabling cacheToolsList=True ensures fast tool discovery during runtime.

Q: Can an OpenAI Agents SDK agent run database migrations on Dokku?

Yes, the agent uses runcommand to execute tasks like migrations in an isolated container. This keeps your web containers running smoothly while the agent handles database schemas.

Q: How do I debug failing container deployments using this integration?

Use getlogs to stream standard output and error logs directly to your agent. The agent analyzes the stack traces to identify why a deployment failed without requiring manual SSH access.

Deploy and manage self-hosted apps on your VPS directly from OpenAI Agents SDK workflows using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dokku MCP to OpenAI Agents SDK

Create your Vinkius account to connect Dokku 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 Dokku with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Control Container Lifecycles from OpenAI Agents SDK

`create_app` sets up the actual reverse-proxy hooks and network allocations on your Dokku VM before your code even arrives. Your Python agent triggers this setup during automated deployment pipelines, verifying host readiness before pushing bytes. When projects retire, `destroy_app` tears down running Docker containers and wipes local DNS routing records instantly. The SDK's built-in guardrails validate these destructive actions before execution, keeping your production VPS safe from accidental agent wipes under this MCP setup.

Dynamic Process Scaling and Restarts

`ps_scale` controls whether a web service runs zero replicas or a worker background task scales up to ten endpoints. OpenAI agents inspect system load via telemetry, then call this tool to adjust resource allocation dynamically based on real-time traffic. If containers hang or need a fresh boot, `ps_restart` tears down old processes and binds updated dynamic ports to Nginx without causing downtime. The agent handles the rolling restart logic, ensuring your self-hosted infrastructure stays responsive under load.

Manage App Environments and Run Migrations

`set_config` injects environment variables into running apps, which triggers a rolling deployment to apply the new database credentials or API tokens. Your agent updates these configurations programmatically, while `unset_config` strips out revoked keys to prevent credential leaks. For database updates, `run_command` spins up an isolated ephemeral container to run migrations safely away from active web traffic. This MCP Server lets your agent execute these administrative tasks directly, tracking every command output inside your OpenAI dashboard.

Setup guide

Set up Dokku 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 Dokku tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` via pip and initialize the server using `MCPServerStreamableHttp` pointing to your Vinkius endpoint. Pass the server instance inside the `mcp_servers` list when creating your Agent. Enabling `cacheToolsList=True` ensures fast tool discovery during runtime.

Yes, the agent uses `run_command` to execute tasks like migrations in an isolated container. This keeps your web containers running smoothly while the agent handles database schemas.

You can define strict guardrails in your Python agent before registering the Dokku tools. The agent checks permissions before invoking `destroy_app` or `unset_config` to prevent unauthorized resource deletion.

Use `get_logs` to stream standard output and error logs directly to your agent. The agent analyzes the stack traces to identify why a deployment failed without requiring manual SSH access.

The server only accesses your Dokku app names, container logs, and environment variables. All communication goes through a secure, encrypted V8 sandbox, ensuring your database credentials and configuration keys are never exposed or stored.

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