Ask which servers a Hetzner Cloud project runs, where they are and which ports are open.
Connect Hetzner Cloud with a project API token and Memtro reads that project's servers with type, location, status and traffic, volumes, networks, load balancers, firewall rules, IPs, snapshots and backups. Each project is its own connection. It reads on demand and there is no hourly sync. When you ask, and once an administrator has granted the action by name, it can power servers on or off, reboot, reset, snapshot or rename them, and grow, attach or detach volumes. Snapshots and bigger volumes add to the monthly bill, and deleting a server or volume is permanent.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Hetzner Cloud tool, reads what it needs, and answers with the source cited.
These tools change something in Hetzner Cloud. 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 Hetzner Cloud 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.
What servers do we run on Hetzner, and in which locations?
Which ports are open on the web firewall?
When was the last snapshot of the database server taken?
Reboot the staging-web-2 server
Grow the db-data volume to 200 GB
Before a penetration test the engineering lead asks which ports are open on Acme's production project. Memtro lists each firewall's inbound rules by protocol, port and source range, and says how many servers each firewall is applied to.
Priya Sharma asks Memtro to snapshot the Brightwave Ltd database server ahead of an upgrade. Memtro shuts it down gracefully as Hetzner recommends, takes the snapshot, which is billed per GB each month until deleted, and powers it back on.
The teams that lean on Hetzner Cloud most, a question each of them asks, and what they connect beside it.
A record in Hetzner Cloud 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 console.hetzner.com open your project → Security → API tokens, generate an API token and choose Read for reading only, or Read & Write so Memtro can act on servers and volumes when asked. Copy it: it is shown once
A token belongs to one project, so add one connection per project. Hetzner Robot (dedicated servers) is a different API and is not covered
In Memtro open Connections → Hetzner Cloud, paste the API token, type the Project name as you know it (it is only a label), and connect
Ask what servers the project runs and where
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Hetzner Cloud tools are the same everywhere.
Only when you ask, and only what it has been granted: power on a Hetzner server; shut down a Hetzner server gracefully; reboot a Hetzner server; power off a Hetzner server (hard); reset a Hetzner server (hard power cycle); take a snapshot of a Hetzner server; rename a Hetzner server; delete a Hetzner server permanently; grow a Hetzner volume; attach a Hetzner volume to a server; detach a Hetzner volume from its server; delete a Hetzner volume permanently. 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.
API token and Project name. In console.hetzner.com open your project → Security → API tokens, generate an API token and choose Read for reading only, or Read & Write so Memtro can act on servers and volumes when asked. Copy it: it is shown once.
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
