- METRICS
- INVENTORY
- DETAILS
- HUMAN
Short answer
How can I check my app health using AI?
Your AI pulls golden metrics like error rates and response times directly from your New Relic account. You get immediate summaries of your monitored entities to spot performance issues. This breakdown shows how your agent handles the data.
The outcomes.
Where your data lands.
The AI translates raw telemetry into clear answers.
METRICS
Instant health summaries
The AI pulls error rates and response times for specific entities. You get a clear picture of performance without opening a dashboard.
INVENTORY
Entity visibility
Your agent lists all monitored services and applications. This makes it easy to find the specific service causing trouble.
DETAILS
Deep dive data
The AI grabs technical metadata for a selected entity. You get the granular context needed to start a fix.
HUMAN
Manual decisions
The AI identifies the trends, but you decide how to fix the code or scale the infrastructure. It provides the facts, you provide the solution.
The workflow
What your AI does when the data arrives.
The AI acts as a bridge between your chat interface and your New Relic telemetry.
Identify services
The agent scans your account to find all active monitored entities.
list_entitiesSummarize performance
It pulls the golden metrics for a specific service to show current health status.
get_apm_summaryFetch specifics
The AI grabs deeper technical metadata for a selected entity to help with troubleshooting.
get_entity_detailsReport findings
The agent presents the error rates and latency trends in plain text for your review.
get_apm_summary
Try it
Copy these to start.
Use these prompts to kick off your monitoring tasks.
Starting points
These are just ideas. Swap out the service names for your actual New Relic entities.
New Relic Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_Rk3fKfy2EBc5U3UTb8bGKnyj2pxBgzOIOazg0CbK/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — New Relic capabilities are ready to use.
{
"mcpServers": {
"new-relic-mcp": {
"url": "https://edge.vinkius.com/vk_preview_Rk3fKfy2EBc5U3UTb8bGKnyj2pxBgzOIOazg0CbK/mcp"
}
}
}List all my monitored entities in New Relic.
Give me an APM summary for the 'Payment Gateway' service.
What are the current error rates for my 'Auth-API' entity?
Get the details for the 'Frontend-Web' service to see its configuration.
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Start here
Connect New Relic once, then ask.
Just click the link to connect your account. Your credentials stay encrypted, and you can immediately start chatting with your data.
Connect New Relic to your AIFAQ
How this task behaves.
- 01
Can the AI change my New Relic alert settings?
No. The AI can only read telemetry and entity data. It cannot modify your configurations or alerts.
- 02
Does the AI delete any monitored entities?
No. This MCP is read-only for your APM data. It cannot delete or create new entities in New Relic.
- 03
Can I use this with Claude?
Yes, as long as you are using an MCP-compatible client like Claude Desktop.
- 04
How does the AI know which service I'm talking about?
It uses the list of entities it finds in your account to match your requests to real services.
- 05
Can the AI fix a high error rate automatically?
No. The AI provides the summary and the data, but you have to perform the actual fix in your environment.
More questions about New Relic? See everything the New Relic Connector can do
Connect New Relic to Claude, Cursor, ChatGPT & more
