newrelic-mcp
MCP server for New Relic workflows, enabling NRQL queries, NerdGraph access, entity lookup, logs, alerts, dashboards, and service levels.
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;.nvmrcisv24) - 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(usuallyhttps://api.newrelic.com/graphql)
EU region: If your New Relic dashboard is at
one.eu.newrelic.com, usehttps://api.eu.newrelic.com/graphqlas yourNERDGRAPH_URLinstead.
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/graphqlwithhttps://api.eu.newrelic.com/graphqlin 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-scoutnewrelic-incident-correlationnewrelic-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
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。
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。
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。