When did it go down
After a customer complaint, support asks when the Northwind portal was down this week. Memtro reads the check's history and finds one outage on Tuesday from 14:05 to 14:19, with the alert delivered by email.
Ask Pingdom whether the site is up, and how much downtime it had last month.
Connect Pingdom with an API token and Memtro reads uptime checks with their status, hostname, last error and response time, a check's up and down history, its uptime percentage and average response time, and the alerts Pingdom delivered. Alert contacts, email addresses and phone numbers are never read. It reads on demand and there is no hourly sync. With a Read-Write token, and once an administrator has granted the action by name, it can create, change, pause or resume checks and schedule maintenance windows that silence alerts. Deleting a check permanently removes its uptime history.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Pingdom tool, reads what it needs, and answers with the source cited.
These tools change something in Pingdom. 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 Pingdom, choosing the same kinds; the tab shows Pingdom's own steps. Each event can start a job, with the event as its input. Pingdom signs nothing, so the long random address is the only check: treat it as a password.
Events and webhooksOnce Pingdom 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.
Is the website up right now?
How much downtime did the site have last month?
When was the API down this week, and for how long?
Which alerts went out yesterday, and for which checks?
Schedule a maintenance window for the checkout checks on Sunday from 02:00 to 04:00
After a customer complaint, support asks when the Northwind portal was down this week. Memtro reads the check's history and finds one outage on Tuesday from 14:05 to 14:19, with the alert delivered by email.
Before Sunday's database move, Raj Patel asks Memtro to stop the API checks paging the on-call team. Memtro schedules a maintenance window from 02:00 to 04:00 on the three API checks, so Pingdom keeps testing them but raises no down alerts during the work.
The teams that lean on Pingdom most, a question each of them asks, and what they connect beside it.
A record in Pingdom 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 My Pingdom open API tokens and generate a token: Read access is enough for reading, and creating, pausing or deleting checks and maintenance windows needs Read-Write
Pingdom's API reference does not give the exact menu path, nor which plans include API access
Copy the token, then in Memtro open Connections → Pingdom, paste the API token and connect
Ask how much downtime the site had last month
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Pingdom tools are the same everywhere.
Only when you ask, and only what it has been granted: create an uptime check; change a check's settings or who it alerts; pause or resume chosen checks; delete a check and its history (permanent); schedule a maintenance window that silences alerts; change a maintenance window; delete a future maintenance window. 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. In My Pingdom open API tokens and generate a token: Read access is enough for reading, and creating, pausing or deleting checks and maintenance windows needs Read-Write.
Yes. Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in Pingdom, choosing the same kinds; the tab shows Pingdom'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