How do I create a Fly.io Personal Access Token?

Log in to the [**Fly.io Dashboard**](https://fly.io/dashboard), go to **Settings** > **Personal Access Tokens**, click **Create**, name your token and copy it immediately — it won't be shown again. Alternatively, use `fly tokens create` from the CLI after authenticating with `fly auth login`.

What is a Fly.io Machine and how does it work?

A Machine is a Fly.io VM (micro-VM) that runs your Docker container image. Each machine has its own CPU, memory, storage and IP address. Machines can be started, stopped, restarted and updated independently. They can run in any of Fly.io's 30+ global regions and are the fundamental compute unit of the platform.

Can I start and stop machines to save costs?

Yes! Use `stop_machine` to halt a machine and release its compute resources, and `start_machine` to boot it again. Stopped machines don't incur compute charges. This is perfect for development/staging environments that don't need to run 24/7. Persistent volumes attached to stopped machines retain all data.

How do I deploy a machine in a specific region?

Use the `create_machine` tool with the `region` parameter set to your desired Fly.io region code. Common regions include: `iad` (Virginia, US), `sjc` (San Jose, US), `nrt` (Tokyo, Japan), `fra` (Frankfurt, Germany), `syd` (Sydney, Australia). The full list is available in the Fly.io documentation.

Fly.io Alternative MCP Server for Google ADK 13 tools — connect in under 2 minutes

Name: Fly.io Alternative
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 13 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add Fly.io Alternative as an MCP tool provider through Vinkius and your ADK agents can call every tool with full schema introspection.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token. get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="flyio_alternative_agent",
    instruction=(
        "You help users interact with Fly.io Alternative "
        "using 13 available tools."
    ),
    tools=[mcp_tools],
)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Fly.io Alternative MCP Server

Connect your Fly.io account to any AI agent and take full control of your edge compute infrastructure through natural conversation.

Google ADK natively supports Fly.io Alternative as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 13 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

App Management — List all apps and retrieve their configuration details including regions, status and organization
Machine Lifecycle — Create, start, stop, restart, update and delete machines (VMs) with full control over CPU, memory, region and image
Machine Inspection — View machine state, configuration, services, health checks and IP addresses
Persistent Volumes — List and create persistent storage volumes that survive machine restarts and redeployments
Certificate Management — Review TLS/SSL certificates and their issuance status for app domains
Global Deployment — Deploy machines across Fly.io's global regions (iad, sjc, nrt, fra, syd, etc.) for low-latency access

The Fly.io Alternative MCP Server exposes 13 tools through the Vinkius. Connect it to Google ADK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Fly.io Alternative to Google ADK via MCP

Follow these steps to integrate the Fly.io Alternative MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 13 tools from Fly.io Alternative via MCP

Why Use Google ADK with the Fly.io Alternative MCP Server

Google ADK provides unique advantages when paired with Fly.io Alternative through the Model Context Protocol.

Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Fly.io Alternative

Production-ready features like session management, evaluation, and deployment come built-in. not bolted on

Seamless integration with Google Cloud services means you can combine Fly.io Alternative tools with BigQuery, Vertex AI, and Cloud Functions

Fly.io Alternative + Google ADK Use Cases

Practical scenarios where Google ADK combined with the Fly.io Alternative MCP Server delivers measurable value.

Enterprise data agents: ADK agents query Fly.io Alternative and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine Fly.io Alternative tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query Fly.io Alternative regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including Fly.io Alternative

Fly.io Alternative MCP Tools for Google ADK (13)

These 13 tools become available when you connect Fly.io Alternative to Google ADK via MCP:

create_machine

io app. Requires the Docker image reference (e.g. "registry.fly.io/myapp:latest"). Optionally set the region (e.g. "iad", "sjc", "nrt"), CPU cores (1-16), memory in MB (256-8192), guest CPU kind (shared, performance) and services config. Machines start in stopped state — use start_machine after creation. Create a new machine in a Fly.io app

create_volume

Requires the volume name and size in gigabytes. Optionally set the region. The volume must be attached to a machine via the machine config mounts. Create a persistent volume for a Fly.io app

delete_machine

The machine cannot be recovered. Optionally set force=true to delete even if the machine has an attached volume. Provide the app_name and machine_id. WARNING: this action is irreversible. Delete a Fly.io machine permanently

get_app

io app including its name, status, regions, organization and network configuration. Provide the app name (not ID). Get details for a specific Fly.io app

get_machine

Provide both the app_name and machine_id. Get details for a specific Fly.io machine

list_apps

io account. Each app is a collection of machines (VMs) running your code across Fly.io's global edge network. Returns app name, status, region and creation date. Use the app name for all subsequent machine, volume and certificate operations. List all Fly.io apps

list_certificates

io app. Each certificate has a hostname, status (issued, pending, failed) and source (lets_encrypt, self_signed, acme). Use this to audit HTTPS certificate status for your app's domains. List TLS/SSL certificates for a Fly.io app

list_machines

io app. Each machine has an ID, name, state (started, stopped, created, destroyed), region, image reference, CPU/memory config and IP addresses. Machines are the fundamental compute units on Fly.io. List machines (VMs) for a Fly.io app

list_volumes

io app. Each volume has an ID, name, state, size in GB, region and the machine it is attached to. Volumes provide persistent storage that survives machine restarts. List persistent volumes for a Fly.io app

restart_machine

Useful for applying configuration changes or recovering from issues. Provide the app_name and machine_id. Restart a Fly.io machine

start_machine

The machine will boot and begin running its configured image. Provide the app_name and machine_id. Start a stopped Fly.io machine

stop_machine

The machine will stop and release its compute resources but retains its configuration and data. Provide the app_name and machine_id. Stop a running Fly.io machine

update_machine

You can modify the Docker image, CPU/memory allocation, services config, mounts and more. Provide the app_name, machine_id and a JSON body with the fields to update. Update a Fly.io machine configuration

Example Prompts for Fly.io Alternative in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with Fly.io Alternative immediately.

"Show me all machines running in my web-api app."

"Start the stopped machine in Tokyo and restart the one in Frankfurt."

"Create a new 10GB volume called 'data' for my database app in Virginia."

Troubleshooting Fly.io Alternative MCP Server with Google ADK

Common issues when connecting Fly.io Alternative to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

Fly.io Alternative + Google ADK FAQ

Common questions about integrating Fly.io Alternative MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.