How to Use the Dokku MCP in Google ADK

Q: How do I register the Dokku MCP Server inside Google ADK?

Import McpToolset from the Python SDK and configure it with your Vinkius HTTP endpoint. Pass this toolset directly into your LlmAgent constructor to expose the deployment commands to Gemini.

Q: How do I restrict which Dokku tools a Google ADK agent can use?

You can use the optional toolnames filter when initializing your McpToolset. This lets you expose read-only tools like listapps while blocking destructive commands.

Q: How can Gemini analyze deployment failures on my Dokku host?

Gemini uses getlogs to stream standard output and error logs directly into its context window. The model's large token limit allows it to parse massive log files to diagnose startup crashes.

Manage your Dokku private cloud deployments directly from Google ADK agents with 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 Google ADK

Create your Vinkius account to connect Dokku 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 Dokku with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise App Lifecycle Management via Google ADK

`create_app` provisions a root app boundary on your Dokku VM, establishing reverse-proxy hooks before code deployment. Gemini models use this tool to set up staging environments automatically when new pull requests register in your database. To clean up resources, `destroy_app` dismantles running Docker containers and removes local VHOST mappings. Your Google ADK agent coordinates these teardowns based on deployment schedules stored in BigQuery, keeping your VPS clean.

Run Isolated Commands and Manage Configs

`run_command` launches a one-off ephemeral container using your production image layers to execute migrations or administrative scripts safely. Google ADK agents trigger these tasks during system updates, keeping database modifications isolated from live web traffic. When credentials change, `set_config` injects new environment variables and triggers a rolling restart of the application cluster. The agent reads updated API keys from your secure enterprise storage and writes them directly to Dokku without manual intervention.

Scale Infrastructure with this MCP Server

`ps_scale` adjusts the number of active web replicas or background workers running on your self-hosted Dokku host. Your agent monitors performance metrics and scales container counts up or down based on resource usage trends. If an app stops responding, `ps_restart` bounces the container processes to restore service while maintaining proxy bindings. This MCP Server gives your Gemini-powered agents direct control over host processes, allowing automated recovery workflows.

Setup guide

Set up Dokku 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 Dokku 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="Dokku_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Dokku 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 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 Google ADK

Import `McpToolset` from the Python SDK and configure it with your Vinkius HTTP endpoint. Pass this toolset directly into your `LlmAgent` constructor to expose the deployment commands to Gemini.

Yes, your agent can query traffic trends in BigQuery and use `ps_scale` to adjust container counts. This allows automated scaling of your self-hosted apps based on historical data.

You can use the optional `tool_names` filter when initializing your `McpToolset`. This lets you expose read-only tools like `list_apps` while blocking destructive commands.

Gemini uses `get_logs` to stream standard output and error logs directly into its context window. The model's large token limit allows it to parse massive log files to diagnose startup crashes.

The server processes your application lists, log files, and environment variables within an isolated, zero-trust sandbox. Your sensitive database tokens and API keys are never cached or exposed to external networks.

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