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

Q: How do I connect Heroku (PaaS) to the OpenAI Agents SDK?

You initialize an MCPServerStreamableHttp object for this MCP Server with your endpoint URL. Pass that inside the mcpservers list to your Agent constructor. Set cacheToolsList=True to speed up tool discovery.

Q: Can the OpenAI Agents SDK create new Heroku (PaaS) apps?

Yes, it can. The agent calls createapp to provision a fresh structural container. It returns the new routing URL and app ID so your pipeline can deploy code to it.

Q: Does this MCP Server support listing add-ons?

It certainly does. The listaddons tool fetches all third-party platform services attached to a specific app. Your agent uses this to audit database sizes or cache tiers.

Q: What happens to my Heroku (PaaS) secrets when the agent reads them?

Data privacy matters here. When your agent runs listconfigvars, it pulls highly confidential database tokens, SendGrid passwords, and OAuth keys into the context window. OpenAI processes this data to answer your prompt, so you must rely on your enterprise data agreements to keep those secrets out of model training pipelines.

Manage your Heroku fleet directly through the OpenAI Agents SDK 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 Heroku (PaaS) MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Control Heroku (PaaS) with OpenAI Agents SDK

This MCP Server exposes your entire Heroku fleet to your agent. You can pull down runtime details with `get_app_info` and map out your regional datacenter placements. If you need to know which containers are crashing, `list_dynos` grabs the internal slug runner telemetry immediately. It handles destructive actions too. Your agent can execute `delete_app` to wipe an active environment. Because you're using OpenAI's built-in guardrails, you can require human approval before the agent actually sends that traffic routing into a persistent 404 state.

Fix Crashes Automatically

Memory leaks happen. When Node.js or Ruby runtimes stall, your AI client catches the alert and fires `restart_all_dynos` to clear the ephemeral memory. It takes seconds. You don't have to wake up and log into the CLI. For hung asynchronous queue workers, you want precision. The agent runs `restart_specific_dyno` to reboot just `worker.2` without dropping active web traffic on your primary frontend replicas.

Orchestrate Database Migrations

Complex schema changes require downtime. Your agent coordinates this by running `toggle_maintenance_mode` to flip the switch before touching the database. This prevents corrupted states from active user sessions. Once the maintenance page is up, the agent verifies the environment with `list_config_vars` to grab the current connection strings. After the migration finishes, it simply toggles maintenance mode off.

Setup guide

Set up Heroku (PaaS) 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 Heroku (PaaS) tools at runtime.
3

Create your Agent

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

Run the agent

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

You initialize an `MCPServerStreamableHttp` object for this MCP Server with your endpoint URL. Pass that inside the `mcp_servers` list to your Agent constructor. Set `cacheToolsList=True` to speed up tool discovery.

Yes, it can. The agent calls `create_app` to provision a fresh structural container. It returns the new routing URL and app ID so your pipeline can deploy code to it.

The SDK natively intercepts tool calls before execution. If the agent tries to run `delete_app`, the framework pauses and waits for your explicit approval or handoff logic to clear the action.

It certainly does. The `list_addons` tool fetches all third-party platform services attached to a specific app. Your agent uses this to audit database sizes or cache tiers.

Data privacy matters here. When your agent runs `list_config_vars`, it pulls highly confidential database tokens, SendGrid passwords, and OAuth keys into the context window. OpenAI processes this data to answer your prompt, so you must rely on your enterprise data agreements to keep those secrets out of model training pipelines.

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