No install? Use cloud.anythingmcp.com directly.
Sign in, install the New Relic in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.
TL;DR
Query New Relic (NRQL, alerts, incidents, dashboards, deployments, entities) from any AI agent via NerdGraph + REST. 7 tools, API-key auth.
💡 Keine Installation? Nutze cloud.anythingmcp.com direkt. Einloggen, Connectors → New Relic klicken, Zugangsdaten einfügen, MCP-API-Key erzeugen — fertig. Kein Docker, kein
git clone, kein lokaler Server.
New Relic + Gemini
Query New Relic (NRQL, alerts, incidents, dashboards, deployments, entities) from any AI agent via NerdGraph + REST. 7 tools, API-key auth.
Voraussetzungen
Die vollständige Setup-Anleitung ist in den Connector eingebaut (im Store sichtbar, wenn du den Connector auswählst). Benötigte Umgebungsvariablen für diesen Connector:
NEW_RELIC_USER_KEY
Schritt 1 — Zugangsdaten holen
This connector wraps two New Relic APIs: the modern NerdGraph (GraphQL) at api.newrelic.com/graphql AND the legacy REST API for deployments (api.newrelic.com/v2).
Setup:
- Log into https://one.newrelic.com → top-right avatar → API keys.
- Create a User key (type: USER, NOT 'License key' / 'Ingest key'). Scopes: account read at minimum; admin if you want to create deployments. Set
NEW_RELIC_USER_KEY. - Note your Account ID (visible in the URL or via the keys page). You'll pass it as a parameter to most tools.
- EU region: if your org is on the EU data centre, change baseUrl to
https://api.eu.newrelic.com.
…(continued in the in-app connector instructions)
Schritt 2 — Adapter installieren
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
Schritt 3 — Connector in Gemini hinzufügen
Gemini CLI liest MCP-Server aus ~/.gemini/settings.json (oder %APPDATA%\gemini\settings.json unter Windows). Hinzufügen:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Hole deinen MCP API Key aus AnythingMCP → Profil → MCP API Keys → Neuer Key.
- Speichern und
geminineu starten. /mcpin Gemini CLI ausführen —New Relicsollte als verfügbar gelistet sein.- Vertex AI Studio:
https://cloud.anythingmcp.com/mcpimtools-Array der Anfrage mit demselben Bearer-Header übergeben.
Verfügbare Tools
| Tool | What it does |
|---|---|
new_relic_run_nrql | Run an NRQL (New Relic Query Language) query against an account |
new_relic_graphql_query | Run an arbitrary NerdGraph (GraphQL) query/mutation |
new_relic_search_entities | Find entities (services, hosts, browsers, mobile apps, dashboards, workloads) by name + domain + type |
new_relic_get_entity | Fetch an entity by GUID — returns the full entity payload (golden metrics, golden tags, recent issues for APM apps) |
new_relic_list_deployments | List recent deployments recorded for an APM application via the legacy REST API |
new_relic_create_deployment | Record a deployment marker on an APM application's chart |
new_relic_recent_incidents | List recent open incidents for an account from the AI/AIops issue stream |
FAQ
Unterstützen Gemini 1.5 Pro oder 2.x MCP? Ja — Gemini CLI ≥ 0.4 und die Vertex AI Tools API akzeptieren MCP httpUrl-Connectors mit Bearer-Header.
Nächste Schritte
War dieser Guide hilfreich?