Morning check
The network lead asks what is down. Memtro lists two devices: an access point at the Acme warehouse down since 06:20 with no response to SNMP, and a UPS in rack B reporting critical battery, both with alerts still firing.
Ask LibreNMS which devices are down and which alerts are still firing.
Connect LibreNMS with an API token and Memtro reads devices with their up or down status, one device in detail, firing and acknowledged alerts, the event log, syslog and alert log, and service checks. SNMP credentials are never returned, and there is no hourly sync. When you ask, and once an administrator has granted them by name, it can put a device into maintenance or acknowledge an alert, which silences notifications, add or change devices, service checks, device groups and alert rules, which decide who gets paged. Deleting a device with its history, a rule, check or group is permanent.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right LibreNMS tool, reads what it needs, and answers with the source cited.
These tools change something in LibreNMS. 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 LibreNMS 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 devices are down right now?
What alerts are still firing at the London office?
When did core-switch-01 last reboot?
Put fw-edge-02 into maintenance for two hours tonight
Acknowledge the UPS battery alert with a note that a replacement is booked
The network lead asks what is down. Memtro lists two devices: an access point at the Acme warehouse down since 06:20 with no response to SNMP, and a UPS in rack B reporting critical battery, both with alerts still firing.
Priya Nair asks Memtro to put the Northwind edge firewall into maintenance from 22:00 for two hours. With the actions granted, Memtro schedules the window, during which nobody is paged about that device, and adds an event log entry for the firmware upgrade.
The teams that lean on LibreNMS most, a question each of them asks, and what they connect beside it.
A record in LibreNMS 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 LibreNMS open Settings → API Settings → API Access and create an API access token for a dedicated user. The token acts with all of its user's rights, so give that user read access to the right devices, and only the rights for the actions an administrator will grant
Add a description such as Memtro and an expiry, then copy the token, shown once
In Connections → LibreNMS in Memtro type the Host name only, a public DNS name with a publicly trusted certificate (a LibreNMS reachable only on the management network cannot be connected), and paste the API token
Ask which devices are down right now
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The LibreNMS tools are the same everywhere.
Only when you ask, and only what it has been granted: add an entry to a device's event log; put a device into maintenance for a time window (silences its alerts); acknowledge a firing alert with a note (stops its notifications); un-acknowledge an alert so its notifications resume; add a device to monitoring; change a device's notes, purpose, display name, location, or disabled, ignored or notification settings; rename a device; queue a rediscovery of a device; delete a device and all its history (permanent); create an alert rule; edit, enable or disable an alert rule, or change who it notifies; delete an alert rule (permanent); add a service check to a device; change, ignore or disable a service check; delete a service check (permanent); create a device group; rename or change a device group's members or rule; delete a device group (permanent); set the notes on a device port. 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.
Host and API token. In LibreNMS open Settings → API Settings → API Access and create an API access token for a dedicated user. The token acts with all of its user's rights, so give that user read access to the right devices, and only the rights for the actions an administrator will grant.
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