Which Uptime.com checks went down this week, and for how long?
Uptime.com connects Memtro to your website and service monitoring. It reads checks with their type, address, up or down state, interval, response time and tags, and a check's uptime and response-time statistics. It reads outages and alerts by check and date, status pages with their components and incidents, and SLA reports. An hourly sync brings recent records into memory. When asked and granted, it can pause or resume a check, ignore an alert, tag, create or delete a check, post and update status page incidents, set a component's status and cancel maintenance. API access needs a paid plan.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Uptime.com tool, reads what it needs, and answers with the source cited.
These tools change something in Uptime.com. 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 Uptime.com 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.
Uptime.com + MemtroWhich checks went down this week, and for how long?
What was the API check's uptime over the last 30 days?
Which checks are paused right now?
Which incidents are open on the public status page?
Pause the staging check while we deploy.
Dan Fletcher, head of infrastructure at Northwind, asked how the customer portal check had done last month. Memtro read its uptime and response-time statistics for the month and listed the outages with their duration and cause. He put both into the monthly service review.
Maya Okafor, support manager at Acme Ltd, asked Memtro to post an incident about slow logins on the public status page and notify subscribers. With the action granted to her team, Memtro posted it with the login component marked degraded. Everyone viewing the page saw it at once, and subscribers were notified.
The teams that lean on Uptime.com most, a question each of them asks, and what they connect beside it.
A record in Uptime.com 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
Cronitor
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
Vanta
Zenduty
Cortex
WorkOS
Kandji
Automox
Huntress
SimpleMDM
Healthchecks.io
Rapid7 InsightVM
ZenhubLog in to uptime.com, open the API Token page, and copy the token or create one. API access needs a paid plan, and the token acts as your user.
In Memtro, open Connections → Uptime.com and paste the API token.
Changes need write or admin access in Uptime.com. An administrator grants the check and status page actions by name to the teams that may use them.
Ask which checks went down this week.
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Uptime.com tools are the same everywhere.
Only when you ask, and only what it has been granted: pause a check; resume a paused check; ignore or un-ignore an alert; add tags to a check; create an HTTP(S) check; delete a check; post a status page incident or maintenance notice; post an update to a status page incident; delete a status page incident; set a status page component's status; cancel a scheduled 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. An hourly sync anchors recently changed Uptime.com records into memory as entities.
API token. Log in to uptime.com, open the API Token page, and copy the token or create one. API access needs a paid plan, and the token acts as your user.
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
