Monthly uptime report
Sarah Chen, operations manager at Acme Ltd, asked for last month's uptime on the customer portal. Memtro read the daily uptime percentages and the downtime periods, each with its start, end and minutes.
Which of our sites have failing checks, and when does a certificate expire?
Oh Dear watches your websites, and Memtro reads the results for you. It reads monitors and which checks are failing, uptime percentages, downtime periods and check run history. It also reads certificate health, broken links, maintenance windows, and status pages with their updates. When asked and granted, it can post, edit or delete a status page update and manage maintenance. It can also run, snooze or switch checks, and add or delete monitors. Oh Dear can tell Memtro when a site goes down, and a job can start on it. Adding monitors needs a full-access token.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Oh Dear tool, reads what it needs, and answers with the source cited.
These tools change something in Oh Dear. 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 Oh Dear, choosing the same kinds; the tab shows Oh Dear's own steps. Each event can start a job, with the event as its input. Oh Dear signs every delivery, and one whose signature does not check out is refused before it is read.
Events and webhooksOnce Oh Dear 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 monitors have failing checks right now?
What was the shop's uptime last month?
Which certificates expire in the next 30 days?
What broken links did the last crawl find on our docs site?
Put the main website into maintenance for 30 minutes.
Sarah Chen, operations manager at Acme Ltd, asked for last month's uptime on the customer portal. Memtro read the daily uptime percentages and the downtime periods, each with its start, end and minutes.
When Oh Dear told Memtro the Northwind shop had gone down, a job started. It read the failing checks and, as granted, posted an update on the public status page that customers saw at once.
The teams that lean on Oh Dear most, a question each of them asks, and what they connect beside it.
A record in Oh Dear 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 Oh Dear, open Profile, then API access, and create a token. Give it full access, or scope it to the monitors and status pages Memtro should see.
In Memtro, open Connections → Oh Dear and paste the API token.
An administrator grants the status page, maintenance and monitor actions by name to the teams that may use them. Events are turned on from the connection's Events tab, then added as a webhook in Oh Dear's team notifications.
Ask which sites have failing checks right now.
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Oh Dear tools are the same everywhere.
Only when you ask, and only what it has been granted: post an update on a public status page; edit a status page update; delete a status page update; start maintenance on a monitor now; stop maintenance on a monitor; schedule a maintenance window; delete a scheduled maintenance window; run a check now; snooze a check's notifications; unsnooze a check; enable or disable a check; add a monitor; delete a monitor. 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 Oh Dear, open Profile, then API access, and create a token. Give it full access, or scope it to the monitors and status pages Memtro should see.
Yes. Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in Oh Dear, choosing the same kinds; the tab shows Oh Dear'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