After an outage
The founder is writing to BigCo about last week's outage. She asks Memtro what customers were told. It reads the incident in full and gives every update posted, the affected components, the timings and the postmortem.
Ask what is down on your status page and what customers were told during an outage.
Connect Statuspage with an API key and Memtro reads the status pages your user can see, incidents and scheduled maintenance with status, impact, affected components and every update posted, each incident's postmortem, and each component's current status. 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 open and update incidents, schedule maintenance, set component status, and write or publish a postmortem, all public at once, and permanently delete incidents or components. Subscribers are emailed or texted only when you ask.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Statuspage tool, reads what it needs, and answers with the source cited.
These tools change something in Statuspage. 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 Statuspage for you. Each event can start a job, with the event as its input. Statuspage signs nothing, so the long random address is the only check: treat it as a password.
Events and webhooksOnce Statuspage 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 anything down on our status page right now?
What did we tell customers during last Tuesday's outage?
Is any maintenance scheduled for this week?
Open an incident for degraded API performance and notify subscribers
Resolve the login incident with an update that the fix is deployed
The founder is writing to BigCo about last week's outage. She asks Memtro what customers were told. It reads the incident in full and gives every update posted, the affected components, the timings and the postmortem.
During a slowdown, on-call engineer Marco Rossi asks Memtro to open an incident on the API component and tell subscribers. Memtro shows the wording, then opens the incident with the API marked as degraded performance. It appears on the public page at once and subscribers are emailed and texted.
The teams that lean on Statuspage most, a question each of them asks, and what they connect beside it.
A record in Statuspage 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.
At manage.statuspage.io open avatar → API info and copy an API key or create one. It is personal, so Memtro sees and changes the pages your user can
If you have several pages, copy the default page id from the same screen
In Memtro open Connections → Statuspage, paste the API key, and the Default page id if you have one, and connect
Ask whether anything is down right now
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Statuspage tools are the same everywhere.
Only when you ask, and only what it has been granted: open an incident on a status page, optionally notifying subscribers; update an incident: post an update, change its status (resolve it), impact or affected components; schedule a maintenance window; delete an incident from the page, permanently; correct the text or time of an update already posted; set a component's status, or rename or redescribe it; add a component to a page; delete a component, permanently; write an incident's draft postmortem, or publish it to the page; save an incident template. 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. At manage.statuspage.io open avatar → API info and copy an API key or create one. It is personal, so Memtro sees and changes the pages your user can.
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 Statuspage 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