
Connect Fly.io to ChatGPT, Claude and Gemini
Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Manage your global container orchestration through natural language.
Developed, maintained, and hosted by Vinkius.
MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
Your AI does the work. We keep it safe and sound.
No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.
Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

Each Connector runs inside its own sealed environment.
Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.
One switch stops every agent. Instantly.
One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.
Spending limits that pause instead of surprise.
Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.
Three controls, built into the layer your AI connects through.
Curated set · 10 capabilities
We ship only the actions that matter.
01-04
4 capabilities in this set.
Part of 10 available through Fly.io.
- 01
Delete machine
Terminates and destroys a Fly Machine immediately. This stops all compute billing and removes ephemeral disk state.
- 02
Exec machine
Runs shell or Bash commands directly inside an active Fly Machine. It's perfect for running ls, ps aux, or database migrations without needing SSH.
- 03
Get app
Retrieves the operational baseline for a specific Fly App. This includes cluster master regions, Wireguard ranges, and Anycast IP assignments.
- 04
Get machine
Fetches exhaustive runtime states for a single Fly Machine. You'll get the execution status, the active docker image digest, and mapped volume points.
05-07
3 capabilities in this set.
Part of 10 available through Fly.io.
- 05
List apps
Lists all Fly.io App spaces belonging to your Organization. Use this to see your collection of microVMs and storage volumes.
- 06
List machines
Returns a list of individual MicroVM endpoints within a Fly App. It provides unique IDs and their specific placement Regions like iad or ams.
- 07
List volumes
Lists the persistent hardware NVMe Volumes attached to an App. This helps you track storage for stateful apps like PostgreSQL.
08-10
3 capabilities in this set.
Part of 10 available through Fly.io.
- 08
Start machine
Boots a previously stopped or suspended Fly Machine. This is useful for restarting crashed worker nodes or paused batch processors.
- 09
Stop machine
Gracefully halts a running Fly.io Machine. Use this to stop compute billing during idle periods.
- 10
Create machine
Provisions a new highly available Edge Machine within an App. Use this to scale horizontal capacity without waiting for full platform deployments.
Real work
What teams actually run
Emergency Scaling
When traffic spikes, tell your agent to create new machines to increase capacity.
Database Migrations
Run internal database diagnostic commands directly on a machine via exec_machine.
Cost Optimization
Ask your agent to find and stop machines that are running during idle cycles.
System Diagnostics
Use the agent to check if a machine is suspended or running a specific docker image.
Automate a task
Put Fly.io to work on one thing.
Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.
One connector, every AI
Fly.io works with the most popular AI clients.
These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.
Claude
ChatGPT
Gemini
Perplexity
Grok
Microsoft Copilot
Cursor
VS Code
Windsurf
JetBrains
Cline
LangChain
Vercel AI SDK
Lovable
Z.ai
Raycast
Qwen Code
Kimi Code
Le ChatBuilding your own app? The connector is yours to use.
You don't need a client to put Fly.io to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.
Observed, not estimated
916ms average. Fast in production.
Fly.io is checked daily against the live service.
- Fastest day
- 712ms
- Slowest day
- 1076ms
- 14-day trend
- Improving-11%
Connect your client
One URL. Every client.
Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.
Preview access · not provider authentication
The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Fly.io, so you can see the experience inside your AI.
It does not authenticate your account with Fly.io. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
Fly.io Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_auAQnLXTRcIdjtuSWpWKn2jSCsP8BhIQLnmdG02e/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Fly.io capabilities are ready to use.
{
"mcpServers": {
"flyio-mcp": {
"url": "https://edge.vinkius.com/vk_preview_auAQnLXTRcIdjtuSWpWKn2jSCsP8BhIQLnmdG02e/mcp"
}
}
}
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Step-by-step instructions for each client are in the guide. How to connect
Guided setup for Claude? Set up Fly.io in Claude and other AIs
Who it's for
Built for the work Fly.io owners hand off.
This MCP is built for engineers who manage containerized workloads on the edge and want to move faster.
- 01
DevOps Engineers
They hand off machine health monitoring and regional scaling tasks to the agent.
- 02
Backend Developers
They use the agent to trigger restarts or run database migrations through chat.
- 03
SRE Teams
They rely on the agent to run real-time diagnostic commands and check execution logs.
FAQ
Questions Fly.io owners ask.
- 01
Do I need to use the Fly CLI to use this MCP?
No. This MCP interacts directly with the Fly.io API, allowing you to perform tasks through your AI client instead of the terminal.
- 02
Is SSH required to run commands on my machines?
No. The exec_machine capability uses the hypervisor API to inject and run shell commands securely without SSH.
- 03
How do I get my Fly.io API token?
You can find your token in the Fly.io Dashboard under Account > Tokens or by running 'fly auth token' in your local terminal.
- 04
Can I manage persistent storage with this MCP?
Yes. You can use the list_volumes capability to see the NVMe volumes attached to your apps.
- 05
Which AI clients can I use with this MCP?
You can use any MCP-compatible client, including Claude, Cursor, and Windsurf.
- 06
Can my agent scale up my application by creating more machines in a specific region?
Yes. Use the 'create_machine' capability. You can specify the region (e.g., 'iad', 'gru') and the Docker image. The agent will command the Fly.io orchestrator to boot up new VM instances instantly to handle increased demand.
- 07
How do I run a database migration or shell command on a live machine via chat?
Use the 'exec_machine' capability. Provide the machine ID and the command. The agent bypasses SSH entirely by interacting directly with the hypervisor API to run your binary alongside the running container securely.
- 08
Can I check the health and image version of my active machines through the agent?
Absolutely. The 'get_machine' capability retrieves exhaustive runtime states, including container health, current executing status (started/stopped), and the precise docker image digest actively booted into memory.
Explore
More in Loved By Devs
Modal (Serverless AI Infrastructure) AI Connector
Manage serverless compute via Modal — audit active apps, track GPU deployments, and monitor network volumes.
ViewStackPath (Edge Computing & CDN API) AI Connector
Manage edge computing workloads and CDN delivery via StackPath — list stacks, deploy workloads, and purge cach
ViewRunPod AI Connector
Integrate your AI securely to RunPod to cleanly quickly provision scalable GPU pods, manage active instances,
ViewPortainer AI Connector
Manage Docker containers and environments via Portainer — list, create, and start containers directly from you
View
Suggestions
Cloudflare AI Connector
AI edge infrastructure: manage Workers, KV, D1, R2, routes, and deployments via agents.
ViewNeon (Serverless PostgreSQL) AI Connector
Manage serverless database infrastructure via Neon — spawn zero-copy branches, audit projects, and monitor com
ViewFly.io AI Connector
Manage edge compute infrastructure via Fly.io — list apps, control machines (VMs), manage volumes and certific
ViewLinode (Akamai) AI Connector
Manage Linode cloud infrastructure—provision compute instances, manage Kubernetes clusters (LKE), and monitor
View
Connect Fly.io to Claude, Cursor, ChatGPT & more
