Where do I find my User API Key?

In New Relic, go to the account dropdown > API keys. Look for a key of type 'USER'. This is required for NerdGraph access.

Can I run any NRQL query through this server?

Yes! Use the `run_nrql` tool and provide your Account ID and the query string. This allows for extremely flexible data retrieval.

What are APM golden metrics?

Golden metrics are the most critical performance indicators for an application: Response Time, Throughput, Error Rate, and Apdex (user satisfaction).

New Relic MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: New Relic
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect New Relic through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to New Relic "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in New Relic?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About New Relic MCP Server

Connect your New Relic account to your AI agent and gain full visibility into your applications and infrastructure through natural conversation using the powerful NerdGraph GraphQL API.

Pydantic AI validates every New Relic tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Entity Discovery — List and search for monitored entities such as APM applications, hosts, containers, and browser apps.
Custom Querying — Execute raw NRQL (New Relic Query Language) strings to retrieve specific datasets and custom metrics.
Golden Metrics — Fetch real-time APM summaries including error rates, Apdex scores, and average response times.
Incident Monitoring — Track active AI-detected issues and open alerts across your accounts.
Dashboard Oversight — List and retrieve configuration details for your custom observability dashboards.
Account Management — Access current user metadata and list all accessible New Relic accounts.
SLO Tracking — Monitor defined Service Level Indicators (SLOs) and performance levels.

The New Relic MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect New Relic to Pydantic AI via MCP

Follow these steps to integrate the New Relic MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from New Relic with type-safe schemas

Why Use Pydantic AI with the New Relic MCP Server

Pydantic AI provides unique advantages when paired with New Relic through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your New Relic integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your New Relic connection logic from agent behavior for testable, maintainable code

New Relic + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the New Relic MCP Server delivers measurable value.

Type-safe data pipelines: query New Relic with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple New Relic tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query New Relic and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock New Relic responses and write comprehensive agent tests

New Relic MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect New Relic to Pydantic AI via MCP:

get_apm_summary

Get APM golden metrics

get_dashboard

Get dashboard configuration

get_entity_details

Get specific entity metadata

get_me

Get current user and account info

list_accounts

List accessible New Relic accounts

list_alerts

List active issues and alerts

list_dashboards

List New Relic dashboards

list_entities

List monitored entities

list_service_levels

List Service Level Indicators (SLOs)

run_nrql

Execute a NRQL query

Example Prompts for New Relic in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with New Relic immediately.

"List all APM applications in my account."

"Show me the error rate and response time for application GUID 'MTIzNDU2fEFQTXxBUFBMSUNBVElPTnwxMjM'."

"Run NRQL: 'SELECT average(duration) FROM Transaction FACET appName SINCE 1 DAY AGO' for account 12345."

Troubleshooting New Relic MCP Server with Pydantic AI

Common issues when connecting New Relic to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

New Relic + Pydantic AI FAQ

Common questions about integrating New Relic MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your New Relic MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.