How to Use the Coolify MCP in Google ADK

Q: Can Google ADK agents manage multiple Coolify nodes?

Yes, the agent can call listservers to identify all attached nodes in your swarm. From there, you can query specific IP properties and connection statuses for each host.

Use the Google ADK to control your entire self-hosted stack via the Coolify 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 Coolify MCP to Google ADK

Create your Vinkius account to connect Coolify 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 Coolify with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map your infrastructure with Google ADK

Use `list_applications` to see every frontend and backend service managed by your nodes. It builds a clear map of project repositories linked to active application UUIDs. This data lets your agents perform downstream mutations like restarting or stopping services. You get full visibility into what is deployed where.

Manage database connections via Google ADK

Query your backend stores using `list_databases` to isolate specific configurations. You can then use `get_database` to pull connection strings for your applications. This workflow ensures your apps link to the correct datastores automatically. It removes the need for manual copy-pasting of credentials.

Execute remote commands with Google ADK

Call `start_application` to spin up suspended containers directly from your agent logic. It manages your service lifecycle by mapping UUIDs to active Docker states. Use this to handle traffic spikes or emergency maintenance. You control your web ingress perimeter without opening a dashboard.

Setup guide

Set up Coolify 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 Coolify 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="Coolify_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Coolify 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 Coolify. 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 Coolify 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 Coolify MCP in Google ADK

It integrates directly through the McpToolset class. You point the server parameters to your endpoint and define which tools to expose to your agent logic.

Yes, the agent can call `list_servers` to identify all attached nodes in your swarm. From there, you can query specific IP properties and connection statuses for each host.

You can apply a tool name filter when initializing the McpToolset. This limits the agent to only the specific operations you decide to authorize.

The agent maintains its context window while interacting with the server. It can digest the output of your infrastructure metrics and make reasoned decisions over long-running build tasks.

The server transmits only the configuration schema and operational metadata necessary for your agent to function. All sensitive environment variables and internal logs stay isolated within your own secure server nodes.

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