How to Use the New Relic MCP in Claude Code

Q: Can I use Claude Code to run New Relic queries in shell scripts?

Yes, you can pipe output from Claude Code after running runnrql to other terminal utilities. This makes it easy to build automated bash scripts that fetch live telemetry.

Q: How do I install the New Relic MCP Server in Claude Code?

Run the claude mcp add command with your Vinkius HTTP transport URL. The tool configuration is saved to your local config file, enabling instant terminal access.

Q: Does Claude Code support monitoring New Relic service level objectives?

Yes, Claude Code can pull your SLO data using listservicelevels. You can quickly check if your services are meeting their targets directly from your terminal prompt.

Q: How do I switch accounts using Claude Code and New Relic?

The agent uses listaccounts to discover all accessible workspaces. You can tell the command-line tool which account ID to target for subsequent telemetry queries.

Connect this New Relic MCP Server to run queries and inspect production alerts directly from your Claude Code terminal.

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 MCP to Claude Code

Create your Vinkius account to connect New Relic 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 with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Triage production incidents from the command line

Claude Code acts as a headless operator, calling `list_alerts` to fetch active New Relic issues directly into your shell. It allows SREs to check system health without opening a web browser during a high-pressure outage. The CLI tool chains these alerts with `get_apm_summary` to see memory or throughput spikes. You can pipe the terminal output to other utilities for rapid, text-based incident diagnostics.

Execute NRQL queries directly in your shell

This MCP Server lets you run raw database and application queries using `run_nrql`. Claude Code processes the tabular data, letting you filter, sort, or format the metrics using standard terminal commands. You can ask Claude Code to run recurring checks or write scripts that trigger based on New Relic query results. It makes performance monitoring a native part of your command-line workflow.

Audit monitored infrastructure via Claude Code

Run audits on your monitored services by calling `list_entities` to fetch all reporting hosts. Claude Code then calls `get_entity_details` to verify that your staging and production servers have matching configurations in New Relic. The agent uses `list_accounts` to jump between different New Relic environments rapidly. It gives you a fast, text-only overview of your entire infrastructure status in your terminal.

Setup guide

Set up New Relic 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-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http new-relic-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 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-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. 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 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 MCP in Claude Code

Yes, you can pipe output from Claude Code after running `run_nrql` to other terminal utilities. This makes it easy to build automated bash scripts that fetch live telemetry.

Run the `claude mcp add` command with your Vinkius HTTP transport URL. The tool configuration is saved to your local config file, enabling instant terminal access.

Yes, Claude Code can pull your SLO data using `list_service_levels`. You can quickly check if your services are meeting their targets directly from your terminal prompt.

The agent uses `list_accounts` to discover all accessible workspaces. You can tell the command-line tool which account ID to target for subsequent telemetry queries.

Your credentials are encrypted and managed securely by the Vinkius platform. Claude Code only interacts with the sandboxed endpoint, meaning your master API keys are never stored in your local terminal history.

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