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

Q: How do I connect the New Relic AI (LLM Observability) server to Windsurf?

Open your /.codeium/windsurf/mcpconfig.json file and add the server configuration under the mcpServers key. Alternatively, use the Settings UI under Cascade to paste your Vinkius MCP configuration details.

Q: Can Cascade run raw queries on my telemetry using New Relic AI (LLM Observability) in Windsurf?

Yes, the agent can execute read-only queries. It uses the customnrql tool to fetch custom telemetry datasets and display them directly in your chat panel.

Q: Does Windsurf support real-time alert policy monitoring with New Relic AI (LLM Observability)?

It does. The agent invokes listalertpolicies over the MCP connection to inspect active thresholds and flag any active incidents that might impact your production models.

Q: How do I view my APM applications within the IDE?

You can ask Cascade to list your services. It will run listapmapps to retrieve all active applications and display their health status.

Let Windsurf autonomously hunt down LLM performance bottlenecks and cost spikes directly in your editor.

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 Windsurf

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Auto-analyze prompt costs in Windsurf

By calling `query_llm_costs`, this MCP Server allows Cascade to query your live LLM expenses when it detects a spike in your billing alerts. The agent pulls these financial metrics without you having to open a browser tab. It combines this data with `list_alert_policies` to pinpoint which specific deployment triggered the budget threshold. You get a clear breakdown of token spend directly in your workspace.

Track latency and errors using this MCP Server

This integration exposes `query_llm_latency` and `query_llm_errors` to let Cascade check performance drops after a code change. Spotting slow model responses becomes simple when your IDE handles the telemetry queries. If a recent commit causes a latency spike, the agent correlates the code diff with live telemetry. The agent identifies slow API calls and suggests immediate optimizations.

Correlate user feedback with custom events

The tool `query_llm_feedback` lets Cascade check how real users interact with your models by pulling recent qualitative scores. This gives you direct insight into how your application performs in production. To keep your telemetry pipeline updated, Cascade runs `post_custom_event` to log custom metrics back to your dashboard. Your agent maintains a clean feedback loop without manual intervention.

Setup guide

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

Prerequisites

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

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my New Relic AI (LLM Observability) payment history." If connected, Cascade will call the New Relic AI (LLM Observability) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Open your `~/.codeium/windsurf/mcp_config.json` file and add the server configuration under the `mcpServers` key. Alternatively, use the Settings UI under Cascade to paste your Vinkius MCP configuration details.

Yes, the agent can execute read-only queries. It uses the `custom_nrql` tool to fetch custom telemetry datasets and display them directly in your chat panel.

It does. The agent invokes `list_alert_policies` over the MCP connection to inspect active thresholds and flag any active incidents that might impact your production models.

You can ask Cascade to list your services. It will run `list_apm_apps` to retrieve all active applications and display their health status.

Your raw telemetry data, including token costs and user feedback, stays inside New Relic's secure cloud. This integration only pulls read-only metrics into your local Windsurf environment over an encrypted connection.

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