newrelic-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@newrelic-mcp Show me open incidents for the last 24 hours"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
newrelic-mcp
An MCP server for New Relic — query your observability data from any AI agent or LLM client that supports the Model Context Protocol.
No official New Relic MCP exists yet. This fills that gap.
Tools
Tool | Description |
| Run any NRQL query |
| Run multiple NRQL queries in one request |
| Search entities by name, type, domain, or tags |
| Get detailed entity info by GUID |
| List NRQL alert conditions |
| Get currently active incidents |
| Get recent deployments for an APM app |
| Get throughput, error rate, latency, saturation |
| Get recent error traces with stacks |
| Get traffic over time |
Related MCP server: New Relic MCP Server
Quick Start
1. Install
# With uv (recommended)
uv pip install .
# Or with pip
pip install .2. Configure
Create a .env file (or set environment variables):
NEW_RELIC_API_KEY=NRAK-XXXXXXXXXXXXXXXXXXXXXXXXXXXX
NEW_RELIC_ACCOUNT_ID=1234567
NEW_RELIC_REGION=USYou need a New Relic User API key.
3. Run
# stdio mode (for local MCP clients like Claude Desktop, Kiro, Cursor)
newrelic-mcp
# HTTP mode (for remote access)
newrelic-mcp --transport http --port 80004. Connect to your MCP client
Claude Desktop / Kiro / Cursor
Add to your MCP config (e.g. ~/.kiro/settings/mcp.json):
{
"mcpServers": {
"newrelic": {
"command": "newrelic-mcp",
"env": {
"NEW_RELIC_API_KEY": "NRAK-XXXXXXXXXXXXXXXXXXXXXXXXXXXX",
"NEW_RELIC_ACCOUNT_ID": "1234567"
}
}
}
}With uvx (no install needed)
{
"mcpServers": {
"newrelic": {
"command": "uvx",
"args": ["newrelic-mcp"],
"env": {
"NEW_RELIC_API_KEY": "NRAK-XXXXXXXXXXXXXXXXXXXXXXXXXXXX",
"NEW_RELIC_ACCOUNT_ID": "1234567"
}
}
}
}Docker
docker compose up -dExamples
Once connected, you can ask your AI agent things like:
"What's the error rate for my payments-api in the last hour?"
"Show me open incidents"
"What deployed recently to the checkout service?"
"Run this NRQL: SELECT count(*) FROM Transaction SINCE 1 day ago FACET appName LIMIT 10"
"What are the golden signals for auth-service?"
Requirements
Python 3.11+
A New Relic account with a User API key
EU Region
If your account is in the EU datacenter, set:
NEW_RELIC_REGION=EUDevelopment
uv sync --all-extras
uv run ruff check .
uv run mypy src/
uv run pytestSee CONTRIBUTING.md for details.
License
MIT — see LICENSE.
Available Tools
10 toolsget_alert_conditionsB
List NRQL alert conditions configured in your account.
Inputs: policy_id. Returns: result
get_deploymentsC
Get recent deployments for an APM application entity.
Inputs: entity_guid (required), limit. Returns: result
get_entityA
Get detailed information about a specific entity by its GUID.
Returns entity metadata including type-specific info (APM language, host metrics, etc.).
Inputs: guid (required). Returns: result
get_error_tracesA
Get recent error traces for an application, including stack traces and messages.
Inputs: app_name (required), limit, since. Returns: result
get_golden_signalsB
Get golden signals for an APM app: throughput, error rate, latency, saturation.
Inputs: app_name (required), since. Returns: object
get_open_incidentsA
Get all currently active (open) incidents/issues from New Relic AI.
Returns issues with their title, priority, affected entities, condition name, and policy name.
Inputs: no named parameters. Returns: result
get_throughput_timeseriesB
Get throughput over time for an application (useful for spotting traffic patterns).
Inputs: app_name (required), since, timeseries. Returns: result
nrql_batch_queryA
Run multiple NRQL queries in a single request (more efficient than individual calls).
Inputs: queries (required). Returns: object
nrql_queryA
Run a NRQL query against your New Relic account and return results.
Use this to query any telemetry data: transactions, errors, spans, logs, infrastructure metrics, custom events, etc.
Inputs: query (required). Returns: result
search_entitiesB
Search for New Relic entities (applications, hosts, services, etc.).
Inputs: name, tags, domain, entity_type. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Tools are mostly distinct: nrql_query and nrql_batch_query overlap in purpose but are clearly differentiated by efficiency, and search_entities vs get_entity serve different stages of entity interaction. Other tools each target a unique domain (alerts, incidents, deployments, golden signals, error traces, throughput), leaving little ambiguity.
All tool names follow a consistent snake_case verb_noun pattern (e.g., get_entity, search_entities, nrql_query). The two nrql tools deviate slightly from get_ but still maintain the same structural style, making the naming predictable and coherent.
With 10 tools, the server covers a broad but focused set of New Relic operations—querying, entity discovery, alerting, performance metrics, and deployment info. This is well-scoped for a monitoring MCP server, neither too sparse nor overloaded.
The surface covers core read-only workflows: flexible NRQL querying, entity lookup, alert/incident awareness, and APM performance details. Minor gaps exist (e.g., no log-specific query but nrql_query handles it, no entity mutation), but for a read-only monitoring server, it covers the essential needs without dead ends.
Related MCP Connectors
Access New Relic observability data through MCP - query metrics, logs, traces, entities, and more
Query your app's logs, metrics and incidents from your AI assistant.
Lets AI agents analyze API metrics, request logs, and traces, and manage apps and alerts.
Manage uptime monitors and incidents and search logs, metrics and traces from an AI assistant.
Related MCP Servers
- FlicenseBqualityDmaintenanceA Model Context Protocol server that enables Large Language Models like Claude to query New Relic logs and metrics using NRQL queries.128-
- AlicenseCqualityBmaintenanceEnables AI assistants to interact with New Relic monitoring and observability data through programmatic access to New Relic APIs. Supports APM management, NRQL queries, alert policies, synthetic monitoring, dashboards, infrastructure monitoring, and deployment tracking.27296 PyPI6MIT
- AlicenseAqualityDmaintenanceEnables AI agents to access New Relic logs and APM data through the NerdGraph API. It allows users to execute NRQL queries, retrieve application performance metrics, and analyze transaction traces using natural language.61MIT
- AlicenseBqualityCmaintenanceEnables natural language access to New Relic for monitoring, querying, and managing dashboards, entities, alerts, and deployments via the Model Context Protocol.529MIT