- STATUS
- STORAGE
- CONFIG
- HUMAN
Short answer
How can I audit my Fly.io setup using AI?
Your AI pulls live data from your Fly.io environment to check app settings, machine health, and volume attachments. You get a clear view of your infrastructure state without running manual CLI commands. This breakdown shows how your agent handles the inspection.
Where every issue lands.
Audit outcomes
The AI organizes your infrastructure data into these specific categories.
STATUS
Machine health checks
The AI uses machine data to report on which instances are running or idling. You see exactly which machines are active.
STORAGE
Volume inventory
Your agent identifies all attached NVMe volumes. You can quickly see which apps are using which storage assets.
CONFIG
App settings review
The AI pulls specific app configurations. You get a summary of how your apps are actually set up in the cloud.
HUMAN
Manual intervention
The AI identifies discrepancies but won't change your settings. You decide when to trigger a deployment or a resize.
The workflow
What your AI does when the data arrives.
The AI acts as a bridge between your natural language questions and the Fly.io API.
Identify targets
The agent first finds all your active applications to establish the scope of the audit.
list_appsCheck app details
It pulls the specific configuration for a chosen app to check for errors or misconfigurations.
get_appInspect hardware
The AI looks at the individual machines within an app to check their current status.
list_machinesVerify storage
It scans for all volumes to ensure your data is correctly attached to the right machines.
list_volumes
Try it
Copy these to start.
Use these prompts to begin your audit.
Starting points
Swap out the app names or volume IDs with your actual Fly.io identifiers.
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"
}
}
}List all my Fly.io apps and tell me which ones are running.
Check the status of the machines in my 'web-api' app.
Show me all the volumes currently attached to my production environment.
Get the configuration for my 'worker-service' app and summarize it.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect Fly.io once, then ask.
One connection secures your credentials, and your AI can immediately start querying your environment. The full tool list is available on the Connector page.
Connect Fly.io to your AIFAQ
How this task behaves
- 01
Can the AI change my app configurations?
No. The AI can only read your current settings. You must make all changes through the Fly.io CLI or dashboard.
- 02
Can the AI restart a machine if it's unhealthy?
No. The AI identifies which machines are unhealthy, but it does not have the capability to perform restarts or deployments.
- 03
Does the AI see my secret environment variables?
No. The tools only provide access to public app configurations and machine statuses.
- 04
How does the AI know which apps belong to me?
It uses your authenticated Fly.io credentials to list only the apps you have permission to see.
- 05
Can I use this to monitor my NVMe volumes?
Yes. The AI can list all volumes and check their status to help you manage your storage.
More questions about Fly.io? See everything the Fly.io Connector can do
Connect Fly.io to Claude, Cursor, ChatGPT & more
