MCP Telemetry

@xprilion

About MCP Telemetry

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

Config

Add this server to your MCP-compatible client using the configuration below.

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

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

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

FAQ from MCP Telemetry

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.

Frequently asked questions

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.

Comments

Basic information

More Developer Tools MCP servers

Apiosk

obcraft

AI-native payments for tools and APIs. Discover, pay for, execute, and publish monetized APIs directly from your agent, settled per call in USDC over x402, through the Model Context Protocol. payments · finance · x402 ·

Codex Pets

astandrik

Public read-only MCP server for discovering, inspecting, installing, and sharing approved Codex-compatible animated pet packs.

Meticulous

MCP server and skills to connect to the Meticulous UI testing platform.

Routebase

Routebase keeps your API's design, docs, contract tests, mocks and monitoring in one living OpenAPI spec so they can't drift apart. Agents work on that same source of truth, under your team's permissions.

Termany

thinkany-ai

Agent-Native Terminal

174