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

Q: How do I configure New Relic AI (LLM Observability) in Cursor?

You add the server details to your .cursor/mcp.json file in your project root. Once configured, Cursor connects to the MCP Server, allowing the editor agent to call telemetry tools during active coding sessions.

Q: Can Cursor use New Relic AI (LLM Observability) to write code based on real metrics?

Yes. Your agent uses the customnrql tool to fetch actual telemetry data, then writes or updates your application code to handle high-traffic or high-latency scenarios based on that real data.

Q: How do I track LLM errors using New Relic AI (LLM Observability) inside Cursor?

You run the queryllmerrors tool to retrieve a list of recent failures. Your agent inspects these errors, locates the failing code in your workspace, and proposes immediate fixes.

Q: Can I view active dashboards from the editor?

Yes. The listdashboards tool retrieves your active telemetry dashboards. This lets the agent know where your metrics are visualized so you can keep your team dashboards updated.

Debug LLM latency, track token costs, and pull New Relic telemetry directly into Cursor while you write code.

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 Cursor

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Inline Latency and Cost Debugging in Cursor

The `query_llm_latency` tool fetches your production response times directly into your editor. This MCP Server lets your AI client analyze performance bottlenecks right alongside the code you are currently refactoring. Combine this with `query_llm_costs` to see the financial impact of your code changes. You get instant feedback on whether a prompt optimization actually reduces your production token spend.

Verify Production Alerts and App Status

The `list_apm_apps` tool lists all your active APM applications directly inside the editor chat. This gives your agent immediate context on which services are running and which ones need attention. Run `list_alert_policies` to inspect the exact thresholds that trigger team notifications. This MCP tool helps you verify that your new code deployment won't accidentally trigger false alarms.

Run NRQL Queries and Track Custom Events via MCP Server

The `custom_nrql` tool runs read-only queries against your entire New Relic database from your editor. This allows your agent to pull raw database metrics and write code that matches real-world usage patterns. You can also use `post_custom_event` to send test telemetry data to your dashboard while debugging. It writes custom events to verify your tracking logic before you commit the code.

Setup guide

Set up New Relic AI (LLM Observability) MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the New Relic AI (LLM Observability) MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent New Relic AI (LLM Observability) transactions." If the MCP tools are loaded correctly, Cursor will call the New Relic AI (LLM Observability) tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

You add the server details to your `.cursor/mcp.json` file in your project root. Once configured, Cursor connects to the MCP Server, allowing the editor agent to call telemetry tools during active coding sessions.

Yes. Your agent uses the `custom_nrql` tool to fetch actual telemetry data, then writes or updates your application code to handle high-traffic or high-latency scenarios based on that real data.

You run the `query_llm_errors` tool to retrieve a list of recent failures. Your agent inspects these errors, locates the failing code in your workspace, and proposes immediate fixes.

Yes. The `list_dashboards` tool retrieves your active telemetry dashboards. This lets the agent know where your metrics are visualized so you can keep your team dashboards updated.

This MCP Server reads your application performance data, specifically LLM latency, token counts, and error rates. All credentials remain encrypted in your local Cursor configuration, and read-only access prevents accidental data modification.

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