Monitoring & incidents · wired today
What can agents actually do with New Relic?
Incidents move faster than humans can tab-switch. The New Relic connector is one of 205 executable connectors and gives agents 5 read-only tools, with the credential held in the vault and every call receipted.
The New Relic tool list, exactly as agents see it
get_user— Get the New Relic user the API key belongs to (who am I: id, name, email)list_accounts— List the New Relic accounts the API key can read (id and name), the account IDs every other tool needsnrql_query— Run a read-only NRQL query against one New Relic account (e.g. SELECT count(*) FROM Transaction SINCE 1 hour ago) and return its resultssearch_entities— Search New Relic entities (applications, hosts, dashboards, monitors) with an entity search query, returning guid, name, domain, type and reporting statelist_alert_policies— List the alert policies in one New Relic account (id, name, incident preference)
Every tool above is read-only. Write surfaces ship only after live testing, and always behind approval gates.
What the New Relic connector needs
You provide API key from your New Relic account; Quox sends it as an API key sent as a header. The credential is stored encrypted in the vault and resolved just-in-time, so agents use it without ever seeing it.
Where to get it: New Relic's own API documentation ↗ covers creating and scoping the credential.
How proven is this?
This connector was blind shape-proven against the real New Relic API: every endpoint it declares answered measurably differently from a deliberately bogus control request, without any account or credential involved. It is Beta: proven against the live API surface, not yet run with a real credential.
New Relic integration FAQ
What can Quox agents do with New Relic?
Agents can run 5 read-only tools against New Relic: get user, list accounts, nrql query, search entities, list alert policies. Every call is receipted in the evidence trail.
What does the New Relic integration need?
You provide API key from your New Relic account; Quox sends it as an API key sent as a header. The credential is stored encrypted in the vault and resolved just-in-time, so agents use it without ever seeing it.
Do agents see my New Relic credentials?
No. Credentials live encrypted in the Quox vault and are resolved server-side at call time. Agents invoke tools; they never receive the underlying secret.
How proven is the New Relic connector?
This connector was blind shape-proven against the real New Relic API: every endpoint it declares answered measurably differently from a deliberately bogus control request, without any account or credential involved. It is Beta: proven against the live API surface, not yet run with a real credential.