How to Use the New Relic MCP in OpenAI Agents SDK

Q: Is it possible to run custom NRQL queries with this setup?

Absolutely. The runnrql tool is included for exactly this purpose. Your agent can construct and execute any NRQL query you'd normally run in the New Relic UI.

Connect your OpenAI Agent to this New Relic MCP Server for production-grade observability and incident response.

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 OpenAI Agents SDK

Create your Vinkius account to connect New Relic to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Incident Triage

Your agent can monitor New Relic for problems on its own. It starts by calling `list_alerts` to see what's currently broken. If it finds a critical issue, this MCP Server lets it dig deeper for context using `get_entity_details` on the affected services or hosts. This isn't just about reading data. You can build specialized agents that hand off tasks. One agent detects the problem, another uses `run_nrql` to query for root causes, and a third summarizes the findings. OpenAI's guardrails ensure each agent only performs its approved actions.

Query Your Entire Stack with the OpenAI Agents SDK

Give your agent direct access to New Relic's Query Language. The `run_nrql` tool is a direct line to your data, letting your agent ask specific questions about performance, errors, or custom business metrics you've instrumented. You can ask it things like "What's the 95th percentile response time for the checkout service in the last hour?" or "Show me the error rate grouped by container name." The agent constructs the query, `run_nrql` executes it, and you get structured data back for analysis or reporting.

Keep a Constant Pulse on Performance

This MCP Server lets your agent track application health without manual checks. Your agent can call `get_apm_summary` for a quick overview of throughput, error rates, and response times for any monitored application. It's a fast way to spot anomalies. For a more focused view, use `list_service_levels` to check SLO compliance. Your agent can periodically check these indicators and trigger a workflow if a service level starts to degrade, all before it breaches the objective. It's proactive monitoring, run by your code.

Setup guide

Set up New Relic MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all New Relic tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives New Relic tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate New Relic tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="New Relic Agent",
            instructions="You have access to New Relic tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

It connects through this Vinkius MCP Server. You just need to install the `openai-agents` library, create an `MCPServerStreamableHttp` instance with your Vinkius endpoint, and pass it to your agent. The tools are discovered automatically.

Yes. While this MCP Server exposes ten tools, the OpenAI Agents SDK allows you to define which tools a specific agent is allowed to execute. This is a key part of its built-in safety and guardrail features.

It's about building reliable, multi-step automations. The SDK handles agent handoffs, action validation, and full tracing. You're not just calling an API; you're building a system that can reason about observability data from New Relic and act on it safely.

Absolutely. The `run_nrql` tool is included for exactly this purpose. Your agent can construct and execute any NRQL query you'd normally run in the New Relic UI.

The connection exposes observability data like metrics, alerts, entity details, and NRQL query results. Vinkius secures it by handling all authentication. Your agent uses a single Vinkius token, and your New Relic credentials are never stored or exposed in your agent's code.

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