4,500+ servers built on MCP Fusion
Vinkius
Fly.io logo
Vinkius
Google ADK logo

How to Use the Fly.io MCP in Google ADK

Manage global Fly.io microVMs and persistent volumes directly from your Gemini workflows using this MCP Server and the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Fly.io MCP on Cursor AI Code Editor MCP Client Fly.io MCP on Claude Desktop App MCP Integration Fly.io MCP on OpenAI Agents SDK MCP Compatible Fly.io MCP on Visual Studio Code MCP Extension Client Fly.io MCP on GitHub Copilot AI Agent MCP Integration Fly.io MCP on Google Gemini AI MCP Integration Fly.io MCP on Lovable AI Development MCP Client Fly.io MCP on Mistral AI Agents MCP Compatible Fly.io MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
Google ADK

Connect Fly.io MCP to Google ADK

Create your Vinkius account to connect Fly.io 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

Long-Context VM Analysis with Google ADK

The `list_machines` tool retrieves unique identifiers and regional placements for all your edge microVMs. Because the Google ADK handles million-token contexts, your agent can ingest the entire state of hundreds of machines at once. Processing this massive payload alongside performance logs lets the agent decide which instances need optimization. It then executes `stop_machine` on idle nodes to cut your edge hosting costs immediately.

Enterprise Storage Mapping via MCP Server

The `list_volumes` tool maps persistent NVMe hardware drives directly to your Google ADK agent. This MCP integration lets your Gemini models cross-reference active database storage with BigQuery operational datasets. When storage limits are reached, the agent triggers `create_machine` to mount new volumes in the correct regional zones. You avoid silent data corruption by letting the agent verify the active mounts via `get_machine`.

Direct Edge Execution and Networking

The `exec_machine` tool runs remote shell commands inside your active containers straight from the Google ADK interface. This lets your agent run migrations, check local disk space, or inspect system processes without manual SSH key setup. To route traffic correctly, the agent inspects Wireguard networks and Anycast IPs using `get_app`. It coordinates these network boundaries across your global deployment by listing active spaces with `list_apps`.

Setup guide

Set up Fly.io 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. 1

    Install Google ADK

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

  2. 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. 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. 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 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_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Fly.io tools via MCP.",
    tools=mcp_tools,
)

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.

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 MCP in Google ADK

The Google ADK takes advantage of Gemini's long-context window to analyze outputs from `list_machines` across dozens of regions. This allows the agent to build a complete mental map of your Fly.io infrastructure in a single turn.
Yes, you can use `exec_machine` to run diagnostic commands inside active Firecracker VMs. The Google ADK captures the standard output, allowing your agent to parse logs and execute follow-up recovery steps.
Your agent queries active hardware storage using `list_volumes` to ensure data safety. The Google ADK then matches these volume IDs against your database configurations before making any scaling decisions.
This MCP Server supports both Stdio and HTTP transports. You configure it using the standard HTTP connection parameters provided in your Vinkius dashboard.
Your Fly.io credentials are never stored on Google Cloud or exposed to the model. Vinkius runs the server in an ephemeral, zero-trust sandbox, passing only the execution outputs of tools like `get_app` to your agent.

Start using the Fly.io MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 10 tools

We've already built the connector for Fly.io. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 10 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.