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

Q: How do I add the New Relic AI (LLM Observability) server to Claude Code?

Run claude mcp add --transport http new-relic-ai-llm-observability -- in your terminal. Make sure all configuration flags are placed before the server name.

Q: Can I use Claude Code to script automated cost checks with New Relic AI (LLM Observability)?

You can write scripts that trigger the agent to run queryllmcosts. It will output the current token spend directly to stdout, allowing you to pipe it to other command-line utilities.

Q: How do I log custom events from my terminal?

The agent uses postcustomevent to send custom telemetry payloads to your dashboard. This is useful for tracking deployment milestones in your CI/CD pipelines.

Run terminal-only commands with Claude Code to track LLM latency, token costs, and custom events directly from your shell.

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 Code

Create your Vinkius account to connect New Relic AI (LLM Observability) to Claude Code 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 Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Command-line telemetry queries using this MCP Server

By running `custom_nrql`, your command-line agent executes read-only queries and pipes the raw performance data into other terminal tools. SREs can now audit model behavior without touching a web browser. This setup lets you build fast shell scripts that monitor system health. You get instant access to your telemetry databases directly from your terminal session.

Pipe LLM latency and cost metrics in Claude Code

The agent uses `query_llm_costs` and `query_llm_latency` over the MCP connection to check your deployment's financial and performance footprint. Tracking resource consumption in CI/CD pipelines becomes straightforward with terminal tools. If a test suite runs too slowly, the agent catches the latency spike before the build finishes. This prevents bad code from reaching your production environment.

Inspect system alerts and feedback loops

Your terminal agent invokes `list_alert_policies` to see what thresholds are currently active on your account. Managing active incidents requires quick access to system states. It can also check `query_llm_feedback` to see how users are rating your models. This gives you a quick way to audit software quality directly from your terminal.

Setup guide

Set up New Relic AI (LLM Observability) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see new-relic-ai-llm-observability-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest New Relic AI (LLM Observability) transactions." It will automatically discover and invoke the available New Relic AI (LLM Observability) tools.

Terminal

claude mcp add --transport http new-relic-ai-llm-observability-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the New Relic AI (LLM Observability) MCP

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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "new-relic-ai-llm-observability-mcp": {
      "type": "url",
      "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 Code

Run `claude mcp add --transport http new-relic-ai-llm-observability -- ` in your terminal. Make sure all configuration flags are placed before the server name.

You can write scripts that trigger the agent to run `query_llm_costs`. It will output the current token spend directly to stdout, allowing you to pipe it to other command-line utilities.

Yes, the agent can execute custom read-only statements using the `custom_nrql` tool. This lets you extract highly specific telemetry tables right inside your shell.

The agent uses `post_custom_event` to send custom telemetry payloads to your dashboard. This is useful for tracking deployment milestones in your CI/CD pipelines.

It accesses read-only telemetry like token costs, latencies, and feedback logs. Vinkius secures this MCP connection using a zero-trust, ephemeral sandbox with one-token authentication.

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