AcademyMCP serversDevelopment

OpenTelemetry MCP Server

Engineering and platform teams that want to investigate traces and LLM calls by asking questions in their AI assistant.

  • Recommendedour rating
  • 204gitHub stars
  • Apache-2.0licence
  • 4 months agolast update
claude mcp add opentelemetry-mcp -e BACKEND_TYPE=jaeger -e BACKEND_URL=http://localhost:16686 -- pipx run opentelemetry-mcp
README.md

Loading the file...

What it does

An MCP server that connects your AI assistant to OpenTelemetry trace backends such as Jaeger, Tempo and Traceloop. You can ask it to look up traces, find errors, compare model performance and track token usage, with specific support for LLM traces.

Use cases

  1. 01Find the most expensive LLM calls in a trace backend
  2. 02Debug errors by asking about failing traces
  3. 03Compare model performance and token usage

Questions about
OpenTelemetry MCP Server.

What is OpenTelemetry MCP Server used for?

Engineering and platform teams that want to investigate traces and LLM calls by asking questions in their AI assistant. An MCP server that connects your AI assistant to OpenTelemetry trace backends such as Jaeger, Tempo and Traceloop. You can ask it to look up traces, find errors, compare model performance and track token usage, with specific support for LLM traces.

How do I install OpenTelemetry MCP Server?

Run this in your terminal: claude mcp add opentelemetry-mcp -e BACKEND_TYPE=jaeger -e BACKEND_URL=http://localhost:16686 -- pipx run opentelemetry-mcp

Is OpenTelemetry MCP Server open source?

Yes. The code is on GitHub (traceloop/opentelemetry-mcp-server) under the Apache-2.0 licence.

Is OpenTelemetry MCP Server safe to use?

It passed our automatic scan for credential theft, hidden instructions and risky install commands. Third party open source software. Sabemos AI does not maintain it. Check the code and permissions before you connect it to company data.