newrelic-mcp

newrelic-mcp

MCP server for New Relic workflows, enabling NRQL queries, NerdGraph access, entity lookup, logs, alerts, dashboards, and service levels.

Category
访问服务器

README

newrelic-mcp

MCP server for New Relic workflows (NRQL, NerdGraph, entity lookup, logs, alerts, dashboards, and service levels).

Prerequisites

  • Node.js 22+ (this repo uses npx; .nvmrc is v24)
  • New Relic account ID
  • New Relic user API key

Required environment variables:

  • ACCOUNT_ID (numeric account id)
  • API_KEY (New Relic user API key)
  • NERDGRAPH_URL (usually https://api.newrelic.com/graphql)

EU region: If your New Relic dashboard is at one.eu.newrelic.com, use https://api.eu.newrelic.com/graphql as your NERDGRAPH_URL instead.

Quick Start

Run the MCP server directly:

# US region (default)
ACCOUNT_ID=123456 \
API_KEY=your_new_relic_user_key \
NERDGRAPH_URL=https://api.newrelic.com/graphql \
npx -y git@github.com:alanhoff/newrelic-mcp.git

# EU region
ACCOUNT_ID=123456 \
API_KEY=your_new_relic_user_key \
NERDGRAPH_URL=https://api.eu.newrelic.com/graphql \
npx -y git@github.com:alanhoff/newrelic-mcp.git

This server speaks MCP over stdio, so it is normally started by an MCP client/agent.

Install In Common CLI Agents

EU region: Replace https://api.newrelic.com/graphql with https://api.eu.newrelic.com/graphql in all configs below if your account is on the EU region.

Codex CLI

Add this to ~/.codex/config.toml:

[mcp_servers.newrelic]
command = "npx"
args = ["-y", "git@github.com:alanhoff/newrelic-mcp.git"]
env = { ACCOUNT_ID = "123456", API_KEY = "your_new_relic_user_key", NERDGRAPH_URL = "https://api.newrelic.com/graphql" }

Verify:

codex mcp list

Claude Code CLI

Use the CLI installer:

claude mcp add-json newrelic '{"type":"stdio","command":"npx","args":["-y","git@github.com:alanhoff/newrelic-mcp.git"],"env":{"ACCOUNT_ID":"123456","API_KEY":"your_new_relic_user_key","NERDGRAPH_URL":"https://api.newrelic.com/graphql"}}'

Verify:

claude mcp get newrelic

Gemini CLI

Add this to ~/.gemini/settings.json (or .gemini/settings.json for project scope):

{
  "mcpServers": {
    "newrelic": {
      "command": "npx",
      "args": ["-y", "git@github.com:alanhoff/newrelic-mcp.git"],
      "env": {
        "ACCOUNT_ID": "123456",
        "API_KEY": "your_new_relic_user_key",
        "NERDGRAPH_URL": "https://api.newrelic.com/graphql"
      }
    }
  }
}

Verify inside Gemini CLI:

/mcp

Cursor (cursor-agent CLI)

Add this to ~/.cursor/mcp.json (or .cursor/mcp.json for project scope):

{
  "mcpServers": {
    "newrelic": {
      "command": "npx",
      "args": ["-y", "git@github.com:alanhoff/newrelic-mcp.git"],
      "env": {
        "ACCOUNT_ID": "123456",
        "API_KEY": "your_new_relic_user_key",
        "NERDGRAPH_URL": "https://api.newrelic.com/graphql"
      }
    }
  }
}

Verify:

cursor-agent mcp list
cursor-agent mcp list-tools newrelic

Install The Skills

This repo ships three skills:

  • newrelic-entity-scout
  • newrelic-incident-correlation
  • newrelic-nrql-debug-ladder

If you are running inside this repository with AGENTS.md, they are already available from .agents/skills/.

To install them globally for Codex:

mkdir -p ~/.codex/skills
for skill in newrelic-entity-scout newrelic-incident-correlation newrelic-nrql-debug-ladder; do
  cp -R ".agents/skills/$skill" "$HOME/.codex/skills/$skill"
done

Alternative (keep them synced to this repo with symlinks):

mkdir -p ~/.codex/skills
for skill in newrelic-entity-scout newrelic-incident-correlation newrelic-nrql-debug-ladder; do
  ln -sfn "$(pwd)/.agents/skills/$skill" "$HOME/.codex/skills/$skill"
done

Local Development

npm install
npm test

Main server entrypoint: index.js

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选
mcp-server-qdrant

mcp-server-qdrant

这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。

官方
精选
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选