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

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

Install the langchain-mcp-adapters package and initialize the client using the Vinkius MCP Server endpoint. You then fetch the tool definitions and pass them directly to your agent executor.

Q: Can I use New Relic AI (LLM Observability) with LangChain to run read-only NRQL queries?

Yes, customnrql lets your agent run any read-only query to fetch system telemetry. It cannot modify your dashboard configurations or write unauthorized data.

Q: How does New Relic AI (LLM Observability) help LangChain handle API errors?

The tool queryllmerrors exposes the exact failure rates of your model endpoints. Your agent can read these errors to automatically switch to a backup model provider when error rates spike.

Q: Can I track user feedback directly inside my LangChain chains?

Yes, you can use queryllmfeedback to pull qualitative ratings from real users. Your chains can use this data to identify which prompt templates are generating poor responses.

Get raw LLM telemetry directly into your LangChain runs via our MCP Server to make real-time routing decisions based on actual costs.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track LLM Spend in LangChain Chains

`query_llm_costs` pulls the actual dollar amount your models are burning right now. LangChain agents can read these financial metrics mid-run to switch from expensive models to cheaper alternatives when a budget threshold is crossed. You don't have to wait for a monthly bill to realize a recursive loop drained your account. Your agent checks the live cost data, compares it against your hard limits, and halts execution before things get out of hand.

Optimize Routing with Latency Data

`query_llm_latency` fetches the exact response times of your model endpoints. This tool gives your LangChain router the telemetry needed to bypass slow providers and send requests to faster backups. Instead of guessing which region is dragging, the agent inspects the P95 latency numbers. If a provider spikes past 1500ms, the chain automatically switches the next tool call to a speedier endpoint.

Feed New Relic AI MCP Server Logs to LangSmith

`post_custom_event` writes custom event telemetry straight into your New Relic dashboard to log agent decisions. Using this tool inside an MCP Server setup allows you to map every step of your multi-agent workflow alongside system metrics. You get a unified view of your application's health without writing messy logging boilerplate. Your LangChain chains run, the server sends the telemetry, and your dashboards update instantly.

Setup guide

Set up New Relic AI (LLM Observability) 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 AI (LLM Observability) 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-ai-llm-observability-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 AI (LLM Observability) 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 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 LangChain

Install the `langchain-mcp-adapters` package and initialize the client using the Vinkius MCP Server endpoint. You then fetch the tool definitions and pass them directly to your agent executor.

Yes, `custom_nrql` lets your agent run any read-only query to fetch system telemetry. It cannot modify your dashboard configurations or write unauthorized data.

The tool `query_llm_errors` exposes the exact failure rates of your model endpoints. Your agent can read these errors to automatically switch to a backup model provider when error rates spike.

Yes, you can use `query_llm_feedback` to pull qualitative ratings from real users. Your chains can use this data to identify which prompt templates are generating poor responses.

Vinkius runs the MCP Server in an isolated V8 sandbox that destroys itself after execution. Your raw token costs, latency metrics, and error logs are sent directly to New Relic using your single endpoint token, meaning no third-party persistent storage ever touches your telemetry.

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