MCP Telemetry

@xprilion

リポジトリ

基本情報

カテゴリ

開発者ツール

トランスポート

stdio

作者

xprilion

MCP Telemetry について

Observability helps. This MCP server adds tracing to all your conversations on Claude (or suitable MCP client) so that you can trace, understand, debug and report on your all your interactions.

#mcp-telemetry#observability#chat-systems

MCP Telemetry の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "MCP Telemetry": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp[cli]",
        "--with",
        "weave",
        "mcp",
        "run",
        "~/mcp-telemetry/server.py"
      ],
      "env": {
        "WANDB_API_KEY": ""
      }
    }
  }
}

MCP Telemetry のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is MCP Telemetry?

MCP Telemetry is a Model Context Protocol server that logs and tracks conversations between users and LLMs, integrating with Weights & Biases Weave for telemetry visualization and analysis.

How to use MCP Telemetry?

Install by adding the provided JSON configuration to your Claude desktop config, setting the WANDB_API_KEY environment variable. The server starts automatically with Claude and logs conversation data, viewable in the Weights & Biases dashboard.

Key features of MCP Telemetry

Start tracing sessions with custom identifiers
Log user inputs, LLM responses, actions, and tool calls
Seamless integration with Weights & Biases Weave
Real-time monitoring of conversation flows
Export and share conversation analytics

Use cases of MCP Telemetry

Trace and analyze conversation flows between users and LLMs
Monitor tool usage patterns and response times
Track error rates and conversation metadata
Share conversation analytics with your team

よくある質問

What data does MCP Telemetry log?

MCP Telemetry automatically logs user messages, LLM responses, tool calls and their results, and conversation metadata.

How do I view my telemetry data?

Log in to your Weights & Biases account, navigate to your project, and you'll see visualizations including conversation flows, tool usage patterns, response times, and error rates.

What are the prerequisites for running MCP Telemetry?

You need a Weights & Biases API key from wandb.ai, and the `uv` command must be available on your system.

How do I start a tracing session?

Prompt Claude to trace a conversation, for example: "Log this conversation with MCP Telemetry, topic will be Cats."

Does MCP Telemetry require any special configuration?

The only required configuration is setting the `WANDB_API_KEY` environment variable in the Claude desktop config.

「開発者ツール」の他のコンテンツ

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

Total CMS

Joe Workman

Read-only Total CMS docs and site content over MCP: exact Twig signatures, field types, schema options, the CLI, release notes and comparisons. No key required.

Meticulous

Mcp-Warden

ermoluk

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

UXMachine

UXMachine measures a web page in a real browser and returns verifiable observations, each with its evidence and its limits. It opens the address on desktop (1280×800) and mobile (390×844) and follows the site's own links