Ask whether the nightly backup job ran, and which Cronitor monitors are failing now.
Connect Cronitor with an API key and Memtro reads cron jobs, heartbeats, checks and sites with their state, schedule and next expected run, a job's recent runs with duration and outcome, issues with their updates, and status pages. It reads on demand and there is no hourly sync. It never sends a ping or publishes to a status page. When asked, and once an administrator has granted the action by name, it can open, change, resolve or permanently delete issues, pause and resume a monitor's alerts, create or clone monitors, and permanently delete a monitor with its history.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Cronitor tool, reads what it needs, and answers with the source cited.
These tools change something in Cronitor. 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 Cronitor 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.
Cronitor + MemtroDid the nightly backup job run last night?
Which monitors are failing right now?
What issues did we have this week, and how long did each last?
Is the public status page showing everything as operational?
Pause alerts on the reporting job for two hours while we migrate it
First thing on Monday the platform lead asks whether the weekend backups ran. Memtro reads the backup job's recent runs and finds Saturday's passed in 14 minutes, while Sunday's never started and the monitor has been failing since 03:00.
Dan Fletcher asks Memtro to pause alerts on the Northwind import job for three hours while the database moves. Memtro pauses that one monitor in Cronitor, which keeps recording runs but alerts nobody, and the pause lifts by itself when the three hours are up.
The teams that lean on Cronitor most, a question each of them asks, and what they connect beside it.
A record in Cronitor 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
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 Cronitor open Settings → API and copy the SDK Integration key, or create a key with monitor:read, issue:read and statuspage:read
Add issue:write only if Memtro should open, change or delete issues, and monitor:write only if it should pause, resume, create, clone or delete monitors. The Telemetry key only sends pings and cannot read anything
In Memtro open Connections → Cronitor, paste the API key and connect
Ask whether the nightly backup job ran
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Cronitor tools are the same everywhere.
Only when you ask, and only what it has been granted: open an internal issue (no update posted, not on any status page); change an issue's name, severity, state or assignee (no update posted, so subscribers are not notified); change the state of, or assign, several issues named by key; delete an issue (permanent); pause a monitor's alerts, for a number of hours or until resumed; resume a paused monitor; create a job or heartbeat monitor (its notification lists are alerted when it fails); clone a monitor (the copy keeps the original's notification lists); delete a monitor and its history (permanent). 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 Cronitor open Settings → API and copy the SDK Integration key, or create a key with monitor:read, issue:read and statuspage:read.
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
