# New Relic — MCP Server

> Ask NRQL questions in plain English and get entity, alert and APM data back.

**Source:** https://mcpplaygroundonline.com/mcp-servers/newrelic  
**Transport:** http  
**Requires auth:** Yes

---

## What it does

The server is built around New Relic’s query layer rather than around dashboards. NRQL is the primary tool: an agent composes a query against events, metrics, logs or traces and reads the result, which covers most of what the platform can answer. Entity search sits alongside it, so a model can resolve "the checkout service" to a real entity GUID before querying it — the step that otherwise produces confidently wrong answers. Alert and incident state is readable for triage, and APM data covers throughput, error rate and transaction traces. Because NRQL spans every telemetry type in one syntax, this server tends to need fewer tool round-trips than observability servers that split logs and metrics into separate tools, which is a real advantage on token cost.

## Tools exposed

- NRQL query — run an arbitrary NRQL statement and read the result set
- entity search — resolve a service or host name to its entity GUID
- APM data — throughput, error rate and transaction detail for a service
- alerts and incidents — read current alert conditions and open incidents
- logs — query log data through the same NRQL surface

## Example queries you can run

- "Write and run the NRQL for error rate by transaction on the checkout service, last 24 hours."
- "Which entities in this account have an open alert right now?"
- "What is the slowest transaction in the API service this week, and how has it trended?"
- "Compare Apdex for the web tier before and after yesterday’s deploy."

## Details

- **Recommended model:** anthropic/claude-sonnet-4.5 — NRQL has its own FACET and TIMESERIES semantics that superficially resemble SQL. Sonnet 4.5 writes it correctly; weaker models produce SQL-shaped queries that fail or silently mislead.
- **Transport:** http
- **Authentication:** Required — A New Relic User API key, sent as an api-key header. The key carries your account scope, so it decides which accounts the agent can read.
- **Hosted endpoint:** https://mcp.newrelic.com/mcp
- **Official source:** [New Relic MCP — official documentation](https://docs.newrelic.com/docs/mcp/)

## Frequently asked questions

### What is the New Relic MCP server?

New Relic’s hosted MCP server at mcp.newrelic.com. It gives an AI assistant NRQL query access plus entity search, APM metrics and alert state, so you can investigate telemetry in conversation rather than in the query builder.

### Do I need to know NRQL to use it?

No — that is largely the point. You describe what you want and the model writes the NRQL. It is still worth reading the query it produces, because a subtly wrong FACET or time window returns a plausible number rather than an error.

### What key does it need?

A User API key, passed as an api-key header. It inherits that user’s account access, so create a dedicated key with the narrowest account scope you need rather than reusing an admin key.

### How does it compare with the Datadog MCP server?

New Relic routes almost everything through NRQL, so one flexible tool answers most questions. Datadog exposes more separate, purpose-built tools. In practice New Relic needs fewer round-trips, Datadog needs less query correctness from the model.

### Can an agent change anything?

The server is oriented toward reading telemetry and alert state rather than mutating configuration. Treat the key as the real boundary: scope it to read-only access and the question stops being about what the tools might allow.

---

_Test this server across 40+ models on MCP Playground: https://mcpplaygroundonline.com/mcp-servers/newrelic — free, no install._