newrelic-mcp
Executes NRQL queries against New Relic via the NerdGraph API, enabling monitoring and observability data retrieval through natural language.
README
New Relic MCP Server
MCP server that executes NRQL queries against New Relic via the NerdGraph GraphQL API.
Tools
execute_nrql— Run an NRQL query against a single New Relic account. Parameters:query(required),account_id(optional ifNEW_RELIC_ACCOUNT_IDis set),timeout_seconds(optional, 1–70).
Requirements
- Python 3.10+
- uv (recommended) or pip
- A New Relic user API key with NerdGraph access
Environment variables
| Variable | Required | Description |
|---|---|---|
NEW_RELIC_API_KEY |
Yes | New Relic user API key for NerdGraph. Create at one.newrelic.com. |
NEW_RELIC_REGION |
No | us (default) or eu for NerdGraph endpoint. |
NEW_RELIC_ACCOUNT_ID |
No | Default account ID when not passed to execute_nrql. |
Copy .env.example to .env and set NEW_RELIC_API_KEY (and optionally the others).
Install
The recommended way is via uvx — no separate install step needed:
{
"mcpServers": {
"newrelic": {
"command": "uvx",
"args": ["newrelic-mcp"],
"env": {
"NEW_RELIC_API_KEY": "YOUR_API_KEY",
"NEW_RELIC_REGION": "us",
"NEW_RELIC_ACCOUNT_ID": "YOUR_ACCOUNT_ID"
}
}
}
}
uvx fetches and runs the package from PyPI automatically.
Or install explicitly with pip:
pip install newrelic-mcp
Claude Code setup
Run this command to register the server (one-time setup):
claude mcp add newrelic --env NEW_RELIC_API_KEY=YOUR_API_KEY --env NEW_RELIC_REGION=us -- uvx newrelic-mcp
Or add it manually to your Claude Code MCP config (~/.claude/settings.json or project .claude/settings.json):
{
"mcpServers": {
"newrelic": {
"command": "uvx",
"args": ["newrelic-mcp"],
"env": {
"NEW_RELIC_API_KEY": "YOUR_API_KEY",
"NEW_RELIC_REGION": "us"
}
}
}
}
Cursor setup
Edit ~/.cursor/mcp.json (global) or .cursor/mcp.json (project-level) and add:
{
"mcpServers": {
"newrelic": {
"command": "uvx",
"args": ["newrelic-mcp"],
"env": {
"NEW_RELIC_API_KEY": "YOUR_API_KEY",
"NEW_RELIC_REGION": "us",
"NEW_RELIC_ACCOUNT_ID": "YOUR_ACCOUNT_ID"
}
}
}
}
Then restart Cursor. Alternatively, use the UI: Cursor Settings → Features → MCP → add a new server with command uvx, arg newrelic-mcp, and the env vars above.
Codex CLI setup
Edit ~/.codex/config.yaml and add:
mcpServers:
newrelic:
type: stdio
command: uvx
args:
- newrelic-mcp
env:
NEW_RELIC_API_KEY: "YOUR_API_KEY"
NEW_RELIC_REGION: "us"
NEW_RELIC_ACCOUNT_ID: "YOUR_ACCOUNT_ID"
Then restart Codex. For project-level config, add the same block to codex.yaml in your project root.
Local development
From the project root:
uv sync
uv run main.py
For debugging with HTTP transport:
MCP_TRANSPORT=http uv run main.py
Then connect to http://localhost:8000/mcp with the MCP Inspector.
Do not commit .env or any file containing your API key.
Example prompts
Use these in Cursor (or any MCP client) to run NRQL via the New Relic MCP server:
-
Run a simple query:
"Run this NRQL:SELECT count(*) FROM Transaction SINCE 1 HOUR AGO" -
Query by account:
"ExecuteSELECT average(duration) FROM Transaction FACET name SINCE 1 day agofor account ID 1234567" -
By Adobe Commerce project:
"Query New Relic for project abc123: show me transaction errors in the last 24 hours"
"Get the last 100 logs for project xyz789"
"List Redis samples for project my-project in the last hour" -
Explore an entity:
"What attributes are available on the Log entity? Run a discovery query."
"Show me one Transaction row so I can see the fields" -
Aggregations and facets:
"Count transactions per app name in the last 6 hours"
"Average response time by transaction name for the last day" -
Time range:
"Run: SELECT * FROM Log WHERE message IS NOT NULL SINCE 2 days ago LIMIT 50"
Set NEW_RELIC_ACCOUNT_ID in the MCP config (or pass it in the prompt) when you are not using an Adobe Commerce project ID; the agent can resolve project ID → account ID when needed.
NRQL and rate limits
- Queries must be valid NRQL (e.g.
SELECT count(*) FROM Transaction SINCE 1 HOUR AGO). - New Relic enforces NRQL rate limits. This server does not retry; failed requests surface as tool errors.
License
MIT
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。