Ask Fly.io why an app's Machine keeps restarting, and how full its volumes are.
Connect Fly.io with an organisation token and your organisation slug and Memtro reads the organisation's apps and their status, the Machines that run them with state, region, image, CPUs and memory, a Machine's recent events, and an app's volumes with size, usage and snapshot retention. Environment variables are never returned. It reads on demand and there is no hourly sync. When asked, and once an administrator has granted the action by name, it can start, stop, restart, suspend or cordon Machines, create apps, snapshot or grow volumes, which is billed, and permanently destroy a Machine or app.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Fly.io tool, reads what it needs, and answers with the source cited.
These tools change something in Fly.io. The model is told to use them only when you ask for exactly that, and an administrator grants each one by name to the teams that may use it; a personal connection acts only after its owner allows it.
Once Fly.io is connected, these are the kinds of things people ask. Plain questions, no syntax. If the answer lives partly in another system you have connected, Memtro looks there too.
Why does the api app's Machine keep restarting?
Which Machines are stopped right now?
How full are the volumes on the postgres app?
Restart the stuck Machine on the checkout app
Snapshot the postgres volume before tonight's migration
The on-call engineer at Acme asks why the checkout app keeps restarting. Memtro lists its Machines, reads the busiest one's recent events and finds repeated exits followed by restarts from flyd over the last hour, with the status of each.
Dan Fletcher sees the Northwind database volume at 9.1 of 10 GB and asks Memtro to snapshot it and grow it to 20 GB. Memtro takes the snapshot, then grows the volume, warning that it can never be shrunk and is billed at the new size, and says whether the Machine needs a restart to see the space.
The teams that lean on Fly.io most, a question each of them asks, and what they connect beside it.
A record in Fly.io is rarely the whole story. Connect the systems that hold the rest and Memtro checks them together, then remembers what it learned so the next question starts further along.
Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.
UptimeRobot
Honeycomb
Cronitor
FireHydrant
StatusCake
GlitchTip
GLPI
Langfuse
LibreNMS
NetBox
Snipe-IT
Woodpecker CI
Zabbix
LangSmith
Helicone
GrowthBook
Drata
Intruder
GitGuardian
Secureframe
ilert
JumpCloud
ConfigCat
Split
Aikido Security
Astronomer
Comet Opik
CrowdStrike Falcon
Detectify
Domotz
LambdaTest
LangWatch
LlamaCloud
Logz.io
Lunary
NinjaOne
Northflank
Portkey
PromptLayer
PRTG Network Monitor
Raygun
Retell AI
Runpod
Shodan
Spike.sh
Squadcast
Tenable
UpGuard
Uptime.com
Vanta
Zenduty
Cortex
WorkOS
Kandji
Automox
Huntress
SimpleMDM
Healthchecks.io
Rapid7 InsightVM
ZenhubIn the fly.io dashboard open Tokens and create an organisation token (a deploy token reaches one app only), or run fly tokens create org -o <your-org>, and copy the whole token
In Memtro open Connections → Fly.io, paste it as the Fly API token and enter the Organisation slug shown by fly orgs list, or personal for your personal organisation
Connect. The connection test lists the organisation's apps to prove the token can read them
Ask why the api app's Machine keeps restarting
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Fly.io tools are the same everywhere.
Only when you ask, and only what it has been granted: start, stop, restart or suspend a Fly Machine; send a signal to a Machine's main process; cordon or uncordon a Machine (take it out of or back into traffic); destroy a Machine (permanent); set a metadata key on a Machine; create an app in the organisation; destroy an app (permanent); snapshot a volume; grow a volume (cannot be shrunk). Every other tool reads, searches or lists. The Connections page labels the tools that act, an administrator grants each one by name to the teams that may use it, and a personal connection acts only after its owner allows it.
A personal connection serves only your own requests. A shared connection serves the organisation: everyone, or only the teams an admin chooses. Admins can always add shared connections; other members need the permission.
Credentials are encrypted at rest. Tool results are cached briefly so agent loops do not repeat identical calls, and the facts the model extracts are saved to your organisation's memory with provenance (system, record and link) so they can be checked and superseded.
Fly API token and Organisation slug. In the fly.io dashboard open Tokens and create an organisation token (a deploy token reaches one app only), or run fly tokens create org -o <your-org>, and copy the whole token.
Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.
Sign in, add a provider key, create an API key and point your tools at Memtro. It takes about five minutes.
7-day free trial · card on file, nothing charged until it ends · cancel any time
