Is anything down
Support hears that sign-in is slow and asks Memtro whether anything is down. Memtro reads the check statuses and finds the login browser check degraded from Frankfurt, with runs taking 9 seconds against a usual 2.
Ask which Checkly checks are failing now, and when and where they started failing.
Connect Checkly with an API key and your account ID and Memtro reads checks with their type, frequency, locations and target URL, whether each is passing, failing or degraded now, raw results, check groups, and the error groups failures cluster into. Check headers, scripts and environment variables are never read. 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 run checks, open and update status page incidents, which are public, schedule maintenance windows, archive error groups, create URL monitors and permanently delete a check.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Checkly tool, reads what it needs, and answers with the source cited.
These tools change something in Checkly. 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, then add the address it shows as a webhook in Checkly, choosing the same kinds; the tab shows Checkly's own steps. Each event can start a job, with the event as its input. Checkly signs every delivery, and one whose signature does not check out is refused before it is read.
Events and webhooksOnce Checkly 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 Checkly checks are failing right now?
When did the login browser check start failing, and from which locations?
Which SSL certificates expire in the next 30 days?
Run the checkout checks again now
Open an incident on the status page saying payments are degraded and we are investigating
Support hears that sign-in is slow and asks Memtro whether anything is down. Memtro reads the check statuses and finds the login browser check degraded from Frankfurt, with runs taking 9 seconds against a usual 2.
Dan Fletcher confirms the Acme payments API is failing and asks Memtro to post it. Memtro opens an incident on the status page with his approved wording and the payments component marked degraded, visible to the public at once, without emailing subscribers, and resolves it when he says the fix is out.
The teams that lean on Checkly most, a question each of them asks, and what they connect beside it.
A record in Checkly 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.
In app.checklyhq.com open User settings → API keys and make an API key. It has your user's access to the account. Copy it, as it is shown once
Copy the account's UUID from Account settings → General
In Memtro open Connections → Checkly, paste the API key and the Account ID, and connect
Ask which checks are failing right now
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Checkly tools are the same everywhere.
Only when you ask, and only what it has been granted: run checks now, by id or by tag, using the run quota; cancel a running Playwright check session; open an incident on a status page (public); post an update to a status page incident, or resolve it (public); rename a status page incident or change its impacted components (public); archive an error group; schedule a maintenance window that silences alerts or pauses checks; change a maintenance window; delete a maintenance window; create a URL monitor; permanently delete a check and its history. 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 and Account ID. In app.checklyhq.com open User settings → API keys and make an API key. It has your user's access to the account. Copy it, as it is shown once.
Yes. Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in Checkly, choosing the same kinds; the tab shows Checkly's own steps. 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