What is alerting
An on-call engineer asks what is alerting. Memtro lists the entities at CRITICAL or WARNING with their severity, the open issues by priority, and the apdex and error rate on the application involved.
NRQL, alert issues and entity health from New Relic, answered in plain English.
Connect New Relic with a User API key and your account id, and Memtro can run any NRQL query, find applications, hosts, browser apps and monitors with their reporting state and alert severity, read one entity's golden metrics, and list open alert issues and the policies behind them. The hourly sync writes each newly opened issue into memory as an event. When asked, and once an administrator has granted each action by name, it can close an open alert issue, which may also resolve the incident in paging tools, and record a deployment marker on an entity.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right New Relic tool, reads what it needs, and answers with the source cited.
These tools change something in New Relic. 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 New Relic, choosing the same kinds; the tab shows New Relic's own steps. Each event can start a job, with the event as its input. New Relic sends a secret with every delivery, and one without it is refused.
Events and webhooksOnce New Relic 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.
What is alerting right now, and how severe is it?
What was the error rate on the checkout-api application in the last hour?
Run SELECT average(duration) FROM Transaction WHERE appName = 'web' TIMESERIES 5 minutes SINCE 1 day ago
Which critical issues opened over the weekend, and are they closed?
Record a deployment of version 4.12.0 on checkout-api with the changelog from this release
An on-call engineer asks what is alerting. Memtro lists the entities at CRITICAL or WARNING with their severity, the open issues by priority, and the apdex and error rate on the application involved.
After a fix ships, Sam Okafor asks Memtro to record the deploy on checkout-api and close the error-rate issue. Memtro adds a deployment marker with the version and commit to the entity's charts, then closes the issue, so New Relic stops notifying and PagerDuty resolves its incident too.
The teams that lean on New Relic most, a question each of them asks, and what they connect beside it.
A record in New Relic 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 one.newrelic.com open the user menu (bottom left) → API keys → Create a key with key type User. A licence or browser key will not work, and a User key sees and changes only what its user can
Copy the key when it is shown: it is shown once. Note the numeric account id beside the account name on the same page
In Memtro open Connections → New Relic, paste the User API key and Account id, set the region to eu if the account lives in the EU data centre, and connect
Ask what is alerting right now
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The New Relic tools are the same everywhere.
Only when you ask, and only what it has been granted: close (resolve) an open alert issue; record a deployment marker (version, changelog, commit) on one entity. 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 New Relic records into memory as entities.
User API key and account id. In one.newrelic.com open the user menu (bottom left) → API keys → Create a key with key type User. A licence or browser key will not work, and a User key sees and changes only what its user can.
Yes. Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in New Relic, choosing the same kinds; the tab shows New Relic'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