traceloop/opentelemetry-mcp-server

Query and analyze LLM traces with AI assistance. Ask Claude to find expensive API calls, debug errors, compare model performance, or track token usage—all from your IDE.
An MCP (Model Context Protocol) server that connects AI assistants to OpenTelemetry trace backends (Jaeger, Tempo, Traceloop), with specialized support for LLM observability through OpenLLMetry semantic conventions.
See it in action:
https://github.com/user-attachments/assets/e2106ef9-0a58-4ba0-8b2b-e114c0b8b4b9
## Table of Contents
Quick Start
Installation
Features
Configuration
Tools Reference
Example Queries
Common Workflows
Troubleshooting
Development
Support
## Quick Start
No installation required! Configure your client to run the server directly from PyPI:
json
// Add to claudedesktopconfig.json:
"mcpServers": {
"opentelemetry-mcp": {
"command": "pipx",
"args": ["run", "opentelemetry-mcp"],
"env": {
"BACKENDTYPE": "jaeger",
"BACKENDURL": "http://localhost:16686"
Or use uvx (alternative):
json
"mcpServers": {
"opentelemetry-mcp": {
"command": "uvx",
"args": ["opentelemetry-mcp"],
"env": {
"BACKENDTYPE": "jaeger",
"BACKENDURL": "http://localhost:16686"
That's it! Ask Claude: "Show me traces with errors from the last hour"
## Installation
### For End Users (Recommended)
bash
# Run without installing (recommended)
pipx run opentelemetry-mcp --backend jaeger --url http://localhost:16686
# Or with uvx
uvx opentelemetry-mcp --backend jaeger --url http://localhost:16686
This approach:
✅ Always uses the latest version
✅ No global installation needed
✅ Isolated environment automatically
✅ Works on all platforms
### Per Client Integration
Claude Desktop
Configure the MCP server in your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claudedesktopconfig.json
Windows: %APPDATA%\Claude\claudedesktopconfig.json
Using pipx (recommended):
json
"mcpServers": {
"opentelemetry-mcp": {
"command": "pipx",
"args": ["run", "opentelemetry-mcp"],
"env": {
"BACKENDTYPE": "jaeger",
"BACKENDURL": "http://localhost:16686"
Using uvx (alternative):
json
"mcpServers": {
"opentelemetry-mcp": {
"command": "uvx",
"args": ["opentelemetry-mcp"],
"env": {
"BACKENDTYPE": "jaeger",
"BACKENDURL": "http://localhost:16686"
For Traceloop backend:
json
"mcpServers": {
"opentelemetry-mcp": {
"command": "pipx",
"args": ["run", "opentelemetry-mcp"],
"env": {
"BACKENDTYPE": "traceloop",
"BACKENDURL": "https://api.traceloop.com",
"BACKENDAPIKEY": "yourtraceloopapikeyhere"
Using the repository instead of pipx?
If you're developing locally with the cloned repository, use one of these configurations:
Option 1: Wrapper script (easy backend switching)
json
"mcpServers": {
"opentelemetry-mcp": {
"command": "/absolute/path/to/opentelemetry-mcp-server/startlocally.sh"
Option 2: UV directly (for multiple backends)
json
"mcpServers": {
"opentelemetry-mcp-jaeger": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/opentelemetry-mcp-server",
"run",
"opentelemetry-mcp"
],
"env": {
"BACKENDTYPE": "jaeger",
"BACKENDURL": "http://localhost:16686"
Claude Code
Claude Code works with MCP servers configured in your Claude Desktop config. Once configured above, you can use the server with Claude Code CLI:
bash
# Verify the server is available