How to Use the New Relic AI (LLM Observability) MCP in Claude

Q: Can I run custom queries with New Relic AI (LLM Observability) inside Claude Desktop?

Yes. You can use the customnrql tool to execute read-only queries directly inside your chat. Your agent processes the raw JSON response to build instant summaries or tables of your app performance.

Q: How do I monitor production costs using New Relic AI (LLM Observability) in Claude Desktop?

You use the queryllmcosts tool to pull actual token spend metrics using this MCP Server. Your agent analyzes these numbers against your usage thresholds to warn you of any sudden budget overruns.

Q: Can I inspect APM applications and user feedback?

Yes. The server provides listapmapps to check your application health and queryllmfeedback to fetch user-submitted ratings. This links qualitative user feedback directly to your system metrics.

Track your LLM costs, latency, and user feedback directly inside Claude Desktop with live New Relic telemetry.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect New Relic AI (LLM Observability) MCP to Claude Desktop

Create your Vinkius account to connect New Relic AI (LLM Observability) to Claude Desktop and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup New Relic AI (LLM Observability) with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct Cost and Latency Audits in Claude Desktop

The `query_llm_costs` tool retrieves your live token spend directly inside your workspace chat. This MCP Server lets your AI client read the raw numbers from New Relic to show you exactly how much your production models cost. You can pair this with `query_llm_latency` to match cost spikes against slow response times. It helps you find the sweet spot between fast responses and your API budget.

Real-time Error Tracking and Alert Audits

The `query_llm_errors` tool pulls active error logs from your LLM applications straight into your desktop workspace. This lets you debug failing prompts or API timeouts without opening a separate browser window. You can also use `list_alert_policies` to verify which alert rules are currently active on your systems. It ensures your team gets notified before users run into repeated failures.

Custom Telemetry and Dashboard Discovery

The `post_custom_event` tool sends custom telemetry data directly to your New Relic account from your chat interface. Logging specific agent states or custom runtimes under the `CustomAITelemetry` event type becomes straightforward. To see where this data goes, use `list_dashboards` to find your active visualization boards. If you need custom metrics, use the MCP tool `custom_nrql` to run read-only queries against your workspace telemetry.

Setup guide

Set up New Relic AI (LLM Observability) MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The New Relic AI (LLM Observability) MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the New Relic AI (LLM Observability) MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under new-relic-ai-llm-observability-mcp.

json

{
  "mcpServers": {
    "new-relic-ai-llm-observability-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by New Relic AI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect New Relic AI (LLM Observability) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about New Relic AI (LLM Observability) MCP in Claude Desktop

This MCP Server connects Claude Desktop to your New Relic telemetry API using your local configuration file. Once added, your agent runs local commands to query metrics and fetch performance data without manual browser searches.

Yes. You can use the `custom_nrql` tool to execute read-only queries directly inside your chat. Your agent processes the raw JSON response to build instant summaries or tables of your app performance.

You use the `query_llm_costs` tool to pull actual token spend metrics using this MCP Server. Your agent analyzes these numbers against your usage thresholds to warn you of any sudden budget overruns.

Yes. The server provides `list_apm_apps` to check your application health and `query_llm_feedback` to fetch user-submitted ratings. This links qualitative user feedback directly to your system metrics.

This MCP Server only accesses your telemetry data, specifically LLM token usage, latency metrics, and user feedback text. All API requests run locally on your machine through the Vinkius sandbox, keeping your API keys secure and isolated from third-party servers.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript