MCP For Claude Marketplace
New Relic AI (LLM Observability)

New Relic AI (LLM Observability) MCP Connector for Claude

A+

Monitor and audit LLM telemetry via New Relic AI — track token costs, p95 latency, and user feedback.

10 tools Official Updated Jun 28, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect your New Relic AI account to any AI agent and take full control of your LLM observability, token cost tracking, and performance analytics through natural conversation.

What you can do

  • LLM Telemetry Audit — Retrieve detailed LLM chat completion messages and prompt inputs directly from your agent to understand literal model behavior in real-time
  • Token Cost Tracking — Execute structural extraction of model costs to calculate exact USD token consumption across your entire AI infrastructure securely
  • Performance Monitoring — Extract p95 latency matrices and average response times to ensure your LLM text generation remains performant and sub-second
  • User Feedback Loop — Retrieve chronological feedback messages and 1-5 rating scores dumped by human supervisors to identify quality regressions natively
  • Custom NRQL Execution — Run sophisticated read-only queries using the New Relic Query Language (NRQL) to extract rich insights from multi-tenant AI datasets instantly
  • Custom Event Injection — Post atomic generic telemetry rows to track internal agent states and custom behavioral markers across your observability pipeline
  • Resource Discovery — Enumerate active APM apps, dashboards, and alert policies to audit your AI environment's structural health and PagerDuty configurations

How it works

  1. Subscribe to this server
  2. Enter your New Relic API Key and Account ID
  3. Start monitoring your AI stack from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • AI Engineers — monitor LLM prompt performance and verify model accuracy through natural conversation without manual dashboard navigation
  • Observability Leads — track global AI token costs and p95 latency benchmarks directly from your workspace to optimize infrastructure spend
  • DevOps Teams — audit APM app health and verify alert policy triggers across multiple AI environments efficiently
llm-monitoringtoken-cost-trackingperformance-analyticsai-observabilitylatency-tracking

10 tools expose this connector's capabilities to your AI agent.

list_alert_policies

Inspect deep internal arrays mitigating specific Plan Math

list_apm_apps

Dispatch an automated validation check routing explicit Gateway history

custom_nrql

Note that NRQL is read-only. Irreversibly vaporize explicit validations extracting rich Churn flags

list_dashboards

Identify precise active arrays spanning native Gateway auth

query_llm_errors

Identify precise active arrays spanning native Hold parsing

query_llm_costs

Perform structural extraction of properties driving active Account logic

query_llm_events

Identify bounded CRM records inside the Headless New Relic Platform

query_llm_feedback

Retrieve explicit Cloud logging tracing explicit Vault limits

query_llm_latency

Provision a highly-available JSON Payload generating hard Customer bindings

post_custom_event

/events` inserting absolute generic `CustomAITelemetry` rows tracking internal agent state. Enumerate explicitly attached structured rules exporting active Billing

See how to talk to your AI agent using New Relic AI (LLM Observability).

Show me the last 5 LLM events for the 'OpenAI' vendor

Retrieving LLM events… I've identified 5 recent messages through the OpenAI module. Highlights: 1) Chat completion 'task-123' (Tokens: 1,500, Cost: $0.03), 2) Prompt 'User Query Alpha' (Status: Success). Would you like to see the literal prompt text for any of these?

What is my total LLM token cost for the last 24 hours?

Retrieving cost metrics… Your total LLM token spend for the last 24 hours is $12.45. This is distributed across 'gpt-4o' ($8.50), 'gpt-3.5-turbo' ($2.45), and 'claude-3-sonnet' ($1.50). Spend is trending 5% lower than yesterday.

Run NRQL: SELECT count(*) FROM LlmEvent WHERE duration > 2 SINCE 1 hour ago

Executing custom NRQL query… I've identified 12 LLM events in the last hour that exceeded 2 seconds in duration. This represents approximately 3% of your total traffic. Would you like me to facet these slow events by model or region?

Yes. Use the `query_llm_costs` tool. Your agent will execute a NRQL aggregation summing the `tokenSpanCost` property from your LLM events over the last 24 hours, faceted by model, to provide a clear financial breakdown.

Related Connectors

SW

Swan MCP

9 tools Official

Empowers algorithmic control over European Bank Accounts. Execute SEPA transfers and manage Virtual Corporate Cards programmatically.

A+ View details →
LI

Liftoff MCP

7 tools Official

Access mobile advertising performance reports and metadata via the Liftoff REST API.

A+ View details →
CO

CoderPad MCP

8 tools Official

Manage technical interviews and assessments via CoderPad — create pads, track interview events, and audit the question bank directly from any AI agent.

F View details →
DI

DingConnect MCP

10 tools Official

Equip your AI agent to manage mobile top-ups, track operators, and monitor account balance via the DingConnect API.

A+ View details →