What is running in Civo, and how much quota do we have left?
Civo hosts your instances and Kubernetes clusters. Memtro reads regions, instances with size, status, IPs and tags, one instance's current load, clusters with node pools and versions, volumes, DNS domains and records, hours of use, and quota against its limits. When asked and granted, it can reboot, stop, start, retag, resize, create or delete an instance, manage DNS domains and records, recycle a Kubernetes node, and delete a cluster or volume. Civo can tell Memtro when an instance, cluster or DNS record changes, and a job can start on it. Civo returns hours of use, not prices.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Civo tool, reads what it needs, and answers with the source cited.
These tools change something in Civo. 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.
Turn events on in the connection's Events tab on the Connections page, choose the kinds you want, and Memtro registers its address with Civo for you. Each event can start a job, with the event as its input. Civo signs every delivery, and one whose signature does not check out is refused before it is read.
Events and webhooksOnce Civo 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.
Which Civo instances are running in LON1?
How much CPU quota headroom do we have left?
Is a Kubernetes upgrade available for our production cluster?
What DNS records does acme.com have in Civo?
How many hours did our instances run this month?
Tom Reilly, a platform engineer at BigCo, asked whether there was room for two more instances in LON1. Memtro read the account's quota and its current instances, and showed him the instance, CPU core and RAM limits against what was in use.
Maya Okafor, a developer at Acme Ltd, asked Memtro to point status.acme.com at a new instance. Memtro read the instance's public IP, added an A record in Civo DNS, and told her it would be live once caches expired.
The teams that lean on Civo most, a question each of them asks, and what they connect beside it.
A record in Civo 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 Civo dashboard, open Profile → Security and copy the API key. It has no scopes, and regenerating it disconnects Memtro.
In Memtro, open Connections → Civo, paste the API key and, if you like, a Default region such as LON1.
The key can change everything the account can, so an administrator grants the instance, DNS and Kubernetes actions by name only to the teams that need them. Events are turned on from the connection's Events tab.
Ask which Civo instances are running in LON1.
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Civo tools are the same everywhere.
Only when you ask, and only what it has been granted: reboot an instance (hard or soft); stop an instance; start a stopped instance; replace an instance's tags; resize an instance to a larger size; create an instance (starts hourly billing); delete an instance; add a DNS domain; delete a DNS domain and all its records; add a DNS record; change a DNS record; delete a DNS record; recycle (rebuild) a Kubernetes node; delete a Kubernetes cluster; delete a volume. 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 key. In the Civo dashboard, open Profile → Security and copy the API key. It has no scopes, and regenerating it disconnects Memtro.
Yes. Turn events on in the connection's Events tab on the Connections page, choose the kinds you want, and Memtro registers its address with Civo for you. A job set to start "When an event arrives" then runs once for each matching event, with the event as its input. The run treats the event as outside data, never as instructions, and anything the run remembers is kept as unverified.
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
