How to Use the New Relic MCP in Pydantic AI

Q: What's the setup process for using the New Relic MCP Server with Pydantic AI?

First, pip install "pydantic-ai-slimmcp". Then, in your code, you create an MCPToolset instance with the Vinkius URL for this server. You pass that toolset into your Agent's constructor, and it's ready to go.

Q: Can I use this New Relic connection with a local LLM in my Pydantic AI agent?

Yes. Pydantic AI is designed to be model-agnostic. The MCPToolset for New Relic works independently of the LLM, so you can pair it with Ollama, Llamafile, or any other local model that Pydantic AI supports.

Add type-safe, validated New Relic observability to any Pydantic AI agent.

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 Pydantic AI

Create your Vinkius account to connect New Relic to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Correct Data, Every Time

The `run_nrql` tool lets your agent execute any query against your New Relic data. But with Pydantic AI, you're not just getting back a blob of JSON. The framework automatically validates the entire response against a Pydantic model. If the API ever returns an unexpected field, a missing key, or the wrong data type, your code will raise a `ValidationError` immediately. No more silent failures or corrupted data making its way into your agent's logic. It's about trusting the data you're acting on.

Build a Type-Safe Monitoring Agent with this MCP Server

This server exposes tools to build a truly reliable monitoring agent. Your agent can call `list_entities` to get a list of services, and Pydantic AI guarantees the result is a proper list of entity objects. Then, it can call `get_entity_details` for a specific service, and again, the structure is checked at runtime. This means you can write agent logic that depends on specific fields being present. You don't need to write defensive code full of `if key in dict` checks. You just access the attributes on the Pydantic model, confident that they exist and have the correct type.

Integrate New Relic with Any LLM

Pydantic AI is model-agnostic, so you can use this New Relic connection with OpenAI, Anthropic, Gemini, or even local models. The tools work the same way regardless of the LLM you choose to power your agent's reasoning. You can build an agent that checks for issues with `list_alerts`, gets a performance snapshot with `get_apm_summary`, and then uses your preferred LLM to summarize the situation. The Pydantic AI framework handles the tool-calling logic and data validation, so you can focus on the agent's task.

Setup guide

Set up New Relic MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "new-relic-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to New Relic tools.",
)

result = await agent.run("List recent New Relic transactions")
print(result.output)

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 Pydantic AI

Pydantic AI automatically validates the API responses from this MCP Server against predefined Pydantic models. If the data from a tool like `get_apm_summary` doesn't match the expected structure, your agent will raise an exception instead of processing bad data.

First, `pip install "pydantic-ai-slim[mcp]"`. Then, in your code, you create an `MCPToolset` instance with the Vinkius URL for this server. You pass that toolset into your `Agent`'s constructor, and it's ready to go.

Yes. Pydantic AI is designed to be model-agnostic. The `MCPToolset` for New Relic works independently of the LLM, so you can pair it with Ollama, Llamafile, or any other local model that Pydantic AI supports.

Your Pydantic AI agent will fail loudly and immediately with a `ValidationError` on the first call that receives an unexpected response. This is a core feature, preventing silent data corruption that could lead to your agent making bad decisions.

Your agent will access your New Relic observability data, such as APM metrics, entity lists, and alert statuses. Vinkius ensures security by isolating the entire process. Your agent communicates with the Vinkius endpoint using a single token; your actual New Relic credentials are never part of your application's configuration.

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