How to Use the Heroku (PaaS) MCP in Google ADK

Q: How do I configure Heroku (PaaS) with Google ADK?

Install the package and set up a McpToolset. Pass your endpoint URL into StreamableHttpServerParameters, then hand that toolset to your LlmAgent.

Q: Can Google ADK filter which Heroku (PaaS) MCP Server tools are exposed?

Yes, you can. Use the toolnames filter when initializing the toolset. This lets you expose listdynos for monitoring while blocking destructive actions like deleteapp.

Q: Will Heroku (PaaS) work with Google ADK long-context models?

The MCP Server works perfectly. The agent runs listaddons and listapps across hundreds of services. Gemini easily holds all that telemetry in its 1M+ token context window for deep analysis.

Q: How do I put an app into maintenance mode?

The agent calls togglemaintenancemode. This flips the switch instantly. It keeps active sessions from corrupting your database during complex schema migrations.

Q: Is it safe to let the agent read Heroku (PaaS) config vars?

You need to be careful here. The listconfigvars tool dumps decrypted application environment variables, including DATABASEURL and OAuth keys. Google Cloud secures the data in transit, but those raw secrets will exist in your Gemini session history.

Give your Google ADK agents direct control over Heroku infrastructure 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 Google ADK

Create your Vinkius account to connect Heroku (PaaS) to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Your Entire Fleet

This MCP Server connects your Gemini models straight to your application infrastructure. Your agent runs `list_apps` to pull every app ID, web URL, and git repository target. It feeds that raw structure right into its massive context window. You can ask the agent to audit your setup. It loops through `get_app_info` to check stack versions like heroku-24 and verify global latency strategies. Gemini digests the entire fleet's architecture in one pass.

Manage Dynos with Google ADK

Your enterprise agents do more than read data. They fix problems. If a worker process hangs up, the AI client triggers `restart_specific_dyno` to reboot that exact container. The main frontend stays up. For widespread memory leaks, the agent escalates to `restart_all_dynos`. It hard reboots all containers tied to the application. This resolves the stall and gets standard request processing moving again.

Provision and Destroy Apps

Infrastructure as code gets conversational. You tell the agent to spin up a staging environment, and it executes `create_app` to provision the structural container. It hands you back the live URL. Cleanup is just as fast. The agent tears down old environments using `delete_app`. This permanently wipes the active app from the platform. It's highly destructive, so you should restrict this tool if you don't want automated deletions.

Setup guide

Set up Heroku (PaaS) MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Heroku (PaaS) tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Heroku (PaaS)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Heroku (PaaS) tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install the package and set up a `McpToolset`. Pass your endpoint URL into `StreamableHttpServerParameters`, then hand that toolset to your `LlmAgent`.

Yes, you can. Use the `tool_names` filter when initializing the toolset. This lets you expose `list_dynos` for monitoring while blocking destructive actions like `delete_app`.

The MCP Server works perfectly. The agent runs `list_addons` and `list_apps` across hundreds of services. Gemini easily holds all that telemetry in its 1M+ token context window for deep analysis.

The agent calls `toggle_maintenance_mode`. This flips the switch instantly. It keeps active sessions from corrupting your database during complex schema migrations.

You need to be careful here. The `list_config_vars` tool dumps decrypted application environment variables, including `DATABASE_URL` and OAuth keys. Google Cloud secures the data in transit, but those raw secrets will exist in your Gemini session history.

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