How to Use the Fly.io Extended MCP in Google ADK

Q: How do I register the Fly.io Extended MCP Server inside a Google ADK agent?

Install the SDK via pip install google-adk and define an McpToolset pointing to your Vinkius HTTP endpoint. Pass this toolset into the tools parameter of your LlmAgent to instantly expose Fly.io infrastructure management capabilities to Gemini.

Q: Can I restrict my Google ADK agent to only use specific tools from the Fly.io Extended MCP Server?

Yes, you can use the optional toolnames filter when configuring your McpToolset in Google ADK. This allows you to expose read-only tools like getmachine and listapps while completely blocking destructive operations like deleteapp.

Q: How does the Fly.io Extended MCP Server assist Google ADK agents in handling network-heavy certificate renewals?

The server provides the createacmecertificate and checkcertificate tools, allowing your Google ADK agent to manage Let's Encrypt certificates. Gemini can monitor the DNS validation status over time and automatically update configurations when the certificate is ready.

Manage Fly.io infrastructure directly from Google ADK using Gemini's long-context reasoning 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 Fly.io Extended MCP to Google ADK

Create your Vinkius account to connect Fly.io Extended 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 Fly.io Extended with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Multi-Region Deployments with Google ADK

`create_app` allows your Google ADK agent to initialize new Fly.io applications based on analysis of BigQuery usage metrics. The Gemini model evaluates regional traffic and determines exactly where to spin up compute resources using `create_machine` with specific image configurations. This MCP Server maps Fly.io's REST API into clean tools that Gemini can invoke within its 1M+ token context window. Your agent can read extensive system logs, correlate them with your cloud database, and execute `update_machine` to adjust CPU or memory allocations.

Manage Fly.io Storage via Google ADK

`create_volume` enables Gemini-powered agents to provision persistent block storage for stateful applications on Fly.io. The Google ADK agent monitors storage usage through Vertex AI pipelines and triggers `extend_volume` when physical disks approach full capacity. Using the `McpToolset` class, you expose storage tools like `list_volumes` and `list_volume_snapshots` directly to your agent. This integration allows the agent to analyze historical snapshot trends in Google Cloud before making decisions to prune old volumes with `delete_volume`.

Intelligent Machine Lifecycle Management

`start_machine` gives your enterprise Google ADK agent direct control over individual Fly.io compute instances during batch processing jobs. The agent initiates the compute nodes, monitors their execution state, and calls `stop_machine` or `suspend_machine` to eliminate idle resource costs. You can use the `tool_names` filter in the ADK setup to restrict the agent's access, ensuring it only executes lifecycle commands without touching app-level configurations. By pairing `wait_machine` with Gemini's reasoning, the agent ensures that machines are fully healthy before routing production traffic.

Setup guide

Set up Fly.io Extended 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 Fly.io Extended 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="Fly.io Extended_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Fly.io Extended 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 Fly.io. 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 Fly.io Extended 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 Fly.io Extended MCP in Google ADK

Install the SDK via `pip install google-adk` and define an `McpToolset` pointing to your Vinkius HTTP endpoint. Pass this toolset into the `tools` parameter of your `LlmAgent` to instantly expose Fly.io infrastructure management capabilities to Gemini.

Yes, you can use the optional `tool_names` filter when configuring your `McpToolset` in Google ADK. This allows you to expose read-only tools like `get_machine` and `list_apps` while completely blocking destructive operations like `delete_app`.

The server provides the `create_acme_certificate` and `check_certificate` tools, allowing your Google ADK agent to manage Let's Encrypt certificates. Gemini can monitor the DNS validation status over time and automatically update configurations when the certificate is ready.

Yes, Google ADK natively supports both transport protocols. For production environments running on Google Cloud, configuring the server with HTTP transport using `StreamableHttpServerParameters` is the recommended path for reliable, long-running agent workflows.

Your Fly.io API tokens, machine configurations, and volume IDs are processed entirely within an ephemeral, zero-trust V8 sandbox hosted by Vinkius. No configuration details or infrastructure credentials are stored on disk or used to train Google's underlying Gemini models.

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