New Relic AI LLM ObservabilityをAIに接続

• 01 / 03レイテンシのデバッグ方法
• 02 / 03モデルの出力品質をモニタリングする方法
• 03 / 03LLMコストの把握方法

最速日

777ms

最遅日

1058ms

14日間の傾向

安定+1%

New Relic AI Connector

準備完了です。MCPクライアントを選択し、セットアップ手順に従ってください。

コネクタリンクhttps://edge.vinkius.com/vk_preview_oqdaAroeFoXBv9yPI4WsHZZZZZuzqhwVoSn1YCyq/mcpコピー

Claude Desktop

以下の手順で数秒で接続できます。

1. 1In Claude Desktop, open Settings → Connectors.
2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3. 3Click Add and start a new chat — New Relic AI capabilities are ready to use.

設定 · claude_desktop_config.jsonコピー

{
  "mcpServers": {
    "new-relic-ai-llm-observability-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_oqdaAroeFoXBv9yPI4WsHZZZZZuzqhwVoSn1YCyq/mcp"
    }
  }
}

• Claude
• ChatGPT
• Cursor
• VS Code
• Windsurf
• Claude Code
• JetBrains
• Cline

各クライアントの手順ガイドはこちらです。 接続方法

Claude向けのガイド付きセットアップ？ New Relic AIをClaudeや他のAIに設定する

このConnectorが対応するすべてのAIクライアントを見る ↑

• 01

  AIエンジニア

  ダッシュボードを操作することなく、対話を通じてLLMプロンプトの性能監視やモデルの精度検証を行います。

• 02

  オブザーバビリティ責任者

  ワークスペースから直接、グローバルなAIトークンコストやp95レイテンシのベンチマークを追跡し、インフラ支出を最適化します。

• 03

  DevOpsチーム

  複数のAI環境におけるAPMアプリの健全性を監査し、アラートポリシーのトリガーを効率的に検証します。

• 01

  How do I connect this MCP to my AI client?

  You subscribe to the MCP on Vinkius, enter your New Relic credentials, and then connect your client like Claude or Cursor with a single click.

• 02

  Can I run custom queries?

  Yes, you can use the custom_nrql capability to run read-only NRQL queries to pull specific insights from your datasets.

• 03

  Does this MCP support cost tracking?

  Yes, the query_llm_costs capability allows you to extract model costs and calculate USD consumption across your infrastructure.

• 04

  Can I track user feedback?

  Yes, you can use the query_llm_feedback capability to retrieve chronological feedback messages and star ratings.

• 05

  Is my data secure?

  Vinkius hosts the MCP and manages your credentials securely, allowing your agent to interact with New Relic through authorized API calls.

• 06

  Can I check my total AI token costs through my agent?

  Yes. Use the query_llm_costs capability. 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.

• 07

  How do I monitor the p95 latency of my LLM generations?

  The query_llm_latency capability retrieves the average duration and latency matrices for your AI providers. Your agent will report the results as a timesheet or summary, helping you identify performance bottlenecks instantly.

• 08

  Can my agent run custom NRQL queries against my telemetry data?

  Absolutely. Use the custom_nrql capability to provide any valid read-only NRQL string. Your agent will query New Relic's NerdGraph API and return the resulting dataset, allowing for complete flexibility in how you analyze your AI operations.

• 

  Helicone (LLM Observability) AIコネクタ

  Monitor LLM usage via Helicone — track requests, analyze costs, measure latency, and manage prompts.

  表示
• 

  Datadog AI (LLM Observability) AIコネクタ

  Monitor LLM performance via Datadog — track token usage, audit prompts, and monitor AI model metrics directly

  表示
• 

  Keywords AI AIコネクタ

  Monitor and optimize your LLM API usage with a unified gateway that tracks costs, latency, and model performan

  表示
• 

  Langfuse (LLM Tracing & Evals) AIコネクタ

  Monitor LLM apps via Langfuse — track traces, manage prompt templates, and audit evaluation scores.

  表示

おすすめ

• 

  LangSmith (LLM Observability & Hub) AIコネクタ

  Monitor LLM apps via LangSmith — track traces, audit prompt templates, and manage evaluation datasets.

  表示
• 

  LLM API Cost Estimator AIコネクタ

  Calculate exact API costs and track session budgets for LLM workflows.

  表示
• 

  LLM API Cost Calculator AIコネクタ

  Estimate and compare the financial impact of LLM usage across different providers.

  表示
• 

  Portkey AIコネクタ

  AI gateway observability: monitor logs, costs, and manage LLM configurations via agents.

  表示