New Relic + Memtro

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.

In Memtro

What you can do with New Relic in Memtro

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.

What it does

  1. 01Any NRQL query, with FACET totals and the time window it covered, up to 500 rows
  2. 02Entity search across APM applications, hosts, browser and mobile apps, monitors and dashboards, by name, type or domain
  3. 03Which entities are alerting right now, with severity, and one entity's golden metrics: apdex, error rate, response time, throughput, CPU
  4. 04Open alert issues by priority and state, up to 30 days back, plus the account's alert policies
  5. 05Hourly sync writes each newly opened alert issue into memory as an event with its entities
  6. 06When asked and granted, closes an open alert issue, which stops its notifications and may resolve the incident in PagerDuty or Opsgenie, and records a deployment marker with version and changelog on an entity

Acts when asked

When you ask it to

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.

  1. 01Close (resolve) an open alert issue
  2. 02Record a deployment marker (version, changelog, commit) on one entity

Events

When it happens

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 webhooks
  • 01An alert issue was created
  • 02An alert issue became active (opened)
  • 03An alert issue closed
In practice

Ask it like you would a colleague

Once 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.

New Relic + Memtro
  • 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

01

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.

02

Closing out the incident

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.

Teams

Where it fits

The teams that lean on New Relic most, a question each of them asks, and what they connect beside it.

Better together

Works with

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.

Also in Engineering and operations

Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.

Setup

How to connect

Connect withUser API key and account id
  1. 1

    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

  2. 2

    Copy the key when it is shown: it is shown once. Note the numeric account id beside the account name on the same page

  3. 3

    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

  4. 4

    Ask what is alerting right now

Also works from

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.

FAQ

Questions

Can Memtro change anything in New Relic?+

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.

Who can use a New Relic connection?+

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.

Does Memtro store my New Relic data?+

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.

How do I connect New Relic?+

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.

Can New Relic start a job?+

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.

Connect New Relic in a few minutes

Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.

Where agents remember your company

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