# OpenTelemetry MCP Server

A Python MCP server that bridges AI coding assistants with the OpenTelemetry ecosystem, giving them live access to documentation, examples, semantic conventions, and instrumentation-quality scoring.

This Model Context Protocol server connects AI coding assistants such as Claude Code, OpenCode, Windsurf, and Cursor to the OpenTelemetry ecosystem, so they can navigate its documentation, generate instrumentation that follows current best practices and semantic conventions, and avoid common anti-patterns. It provides repository and issue browsing and search across OpenTelemetry repositories, language-specific examples and documentation, access to semantic-convention attribute definitions, and instrumentation scoring against the instrumentation-score specification, plus prompts that analyze code and suggest instrumentation.

It is self-instrumented with full distributed tracing, supports stdio, HTTP, and SSE transports, and includes Kubernetes manifests and health checks for production deployment. GitHub access for the repository and issue tools is authenticated through a personal access token for individual use or a GitHub App for hosted deployments.

Requirements are Python 3.13 or later and the `uv` package manager.

Website: https://github.com/liatrio-labs/otel-instrumentation-mcp