How to Use the New Relic MCP in LangChain

Build complex reasoning chains in LangChain that pull live APM metrics and alert status directly from your New Relic account.

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 LangChain

Create your Vinkius account to connect New Relic to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain New Relic data in LangChain

Feed `get_apm_summary` outputs directly into your agent's reasoning chain. Your chain now makes decisions based on real-time latency instead of static prompts. This MCP server acts as the primary data source for your LangGraph workflows. Link `list_alerts` results to downstream tasks to automate incident triage.

Observe your LangChain agent logic

Pipe your agent's tool execution history through LangSmith to debug your pipeline. You see exactly when the agent calls `run_nrql` and what data it receives. Tracing every step ensures your multi-step logic holds up under pressure. You catch errors in query formation before they hit your production telemetry.

Manage New Relic entities via LangChain

Use `list_entities` to map your infrastructure topology within your agent's context. Your code now understands exactly which services it needs to monitor. Pass these details to `get_entity_details` to fetch metadata for specific pods or nodes. Your agent handles the discovery phase without manual input.

Setup guide

Set up New Relic MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes New Relic tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "new-relic-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent New Relic transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install the necessary adapters and initialize the MultiServerMCPClient with your endpoint URL. Once connected, use client.get_tools() to inject the tools into your agent's toolset.

Yes, define your agent's workflow to include the NRQL tool as a potential action. The agent determines when to run these queries based on the task description you provide.

Your session context holds the data returned by the tool calls. By default, this data is stateless, but you can use client.session() to keep that context alive across requests.

Vinkius manages the auth layer, so you only need to pass your endpoint token. Your keys never touch your agent code, keeping your telemetry access secure.

Your APM metrics and entity metadata are isolated within your specific agent instance. No other processes can read the raw telemetry pulled during your session.

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