What environment variables are required?
`NEW_RELIC_API_KEY` is required. `NEW_RELIC_ACCOUNT_ID` is optional; if not set, you must provide `target_account_id` per tool call.
@cloudbring
基本信息
Run NRQL, NerdGraph, and REST v2 operations to query data, manage incidents, create synthetics, and annotate deployments — all from your MCP client.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"newrelic": {
"command": "npx",
"args": [
"-y",
"newrelic-mcp"
],
"env": {
"NEW_RELIC_API_KEY": "your-api-key-here",
"NEW_RELIC_ACCOUNT_ID": "your-account-id"
}
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
New Relic MCP Server is a Model Context Protocol server that connects AI assistants directly to New Relic’s observability platform. It provides a suite of tools for querying data (NRQL, NerdGraph), managing entities, incidents, alert policies, APM applications, Synthetics monitors, and deployments. Designed for SRE copilots, it enables natural‑language interaction with New Relic.
Install the server with npx -y newrelic-mcp. Configure it in your MCP client’s JSON by setting NEW_RELIC_API_KEY (required) and optionally NEW_RELIC_ACCOUNT_ID. The default account ID can be overridden per tool call using the target_account_id parameter. The recommended system prompt guides the assistant on which tool to use for each task (e.g., run_nrql_query for aggregate analytics, REST tools for deployments).
confirm: true.`NEW_RELIC_API_KEY` is required. `NEW_RELIC_ACCOUNT_ID` is optional; if not set, you must provide `target_account_id` per tool call.
Deletion requires explicit user confirmation. Set the `confirm: true` parameter when calling `delete_deployment`.
Yes. REST v2 tools are region‑aware and can be configured per request to target the correct New Relic region (e.g., US, EU).
Use `run_nrql_query` for aggregate analytics and timeseries data. Use `run_nerdgraph_query` for graph‑shaped data and entities/alerts APIs.
Yes. You need a valid New Relic User API Key and an Account ID to use the server.
Model Context Protocol (MCP) server for TranscriptFetch: fetch YouTube transcripts, search, channels, and playlists from any MCP client.
Console, Backend and CLI to manage Capgo Instant update and Native build for Capacitor apps Build and upload to app store your mobile app
Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R

Collide is the multiplayer layer for AI coding agents, and it pays for itself. Expert orchestration across every agent on your repo saves teams tens to hundreds of dollars a day in token burn. Run Claude Code, Codex, Cu

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.
评论