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

Q: How does LlamaIndex ingest data from New Relic AI (LLM Observability)?

You use the llama-index-tools-mcp package to connect to the Vinkius MCP Server. The tools are converted into a tool spec that your agent uses to query telemetry data on demand.

Q: Can I use New Relic AI (LLM Observability) to build a self-healing RAG pipeline in LlamaIndex?

Yes, by using queryllmerrors and queryllmlatency to monitor performance. If the agent detects high latency or error rates, it can dynamically route queries to a faster vector index.

Q: Does the New Relic AI (LLM Observability) MCP Server support dashboard discovery in LlamaIndex?

Yes, the listdashboards tool allows your agent to find existing dashboards in your account. The agent can then use this info to point you to the right visualization.

Q: Can my agent post telemetry events directly from LlamaIndex?

Yes, postcustomevent lets your pipeline send custom telemetry back to New Relic. This is useful for logging specific retrieval events or agent decisions.

Index your production LLM telemetry from our MCP Server into LlamaIndex to query real-time cost and latency data.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Cost Metrics with LlamaIndex and MCP Server

`query_llm_costs` extracts the exact token costs associated with your production model runs. This tool converts financial telemetry into searchable documents so your RAG pipeline can answer questions about operational spend. You can query your knowledge base to find out which indexes are costing the most to run. The agent grabs the latest cost data, indexes it, and lets you ask plain-English questions about your budget.

Monitor Vector Search Performance

`query_llm_latency` retrieves the execution times for your LLM queries. LlamaIndex pipelines use this tool to track if retrieval-augmented generation is slowing down due to sluggish model endpoints. By indexing these latency profiles, your system learns which document retrievals take too long. You can run automated checks to ensure your P95 latency stays under your 800ms target.

Analyze User Feedback and Errors

`query_llm_feedback` retrieves qualitative ratings and comments from your production users. Combining this with `query_llm_errors` allows your index to map poor user ratings directly to underlying system failures. This gives you a clear picture of why users are frustrated. Your agent parses the bad feedback, checks the error logs from the same timeframe, and highlights the exact prompts that caused the failures.

Setup guide

Set up New Relic AI (LLM Observability) MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all New Relic AI (LLM Observability) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to New Relic AI (LLM Observability) tools.",
)
response = await agent.run("List recent New Relic AI (LLM Observability) data")

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 LlamaIndex

You use the `llama-index-tools-mcp` package to connect to the Vinkius MCP Server. The tools are converted into a tool spec that your agent uses to query telemetry data on demand.

Yes, by using `query_llm_errors` and `query_llm_latency` to monitor performance. If the agent detects high latency or error rates, it can dynamically route queries to a faster vector index.

Yes, the `list_dashboards` tool allows your agent to find existing dashboards in your account. The agent can then use this info to point you to the right visualization.

Yes, `post_custom_event` lets your pipeline send custom telemetry back to New Relic. This is useful for logging specific retrieval events or agent decisions.

All API requests are processed inside ephemeral, zero-trust V8 isolates. Your token costs, error rates, and user feedback logs are transmitted using encrypted connections directly to your New Relic account, leaving no data footprint behind.

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