---
title: "OpenTelemetry MCP Server: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/mcp-servers/opentelemetry-mcp/
description: "Queries LLM application traces in Jaeger, Grafana Tempo or Traceloop, with tools that aggregate token usage by model and find slow, token-heavy or failing traces."
---

# OpenTelemetry MCP Server: review, setup & limitations · Undominated.ai

> Queries LLM application traces in Jaeger, Grafana Tempo or Traceloop, with tools that aggregate token usage by model and find slow, token-heavy or failing traces.

[← Explore all mcp servers](/mcp-servers/)

LLM OBSERVABILITY / Traceloop

# OpenTelemetry MCP Server

Queries LLM application traces in Jaeger, Grafana Tempo or Traceloop, with tools that aggregate token usage by model and find slow, token-heavy or failing traces.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/traceloop/opentelemetry-mcp-server)

SOURCE REVIEW

 Reviewed 2026-10-13
 Evidence 3 linked sources
 Publisher Traceloop
 Licence [Apache-2.0 ↗](https://github.com/traceloop/opentelemetry-mcp-server/blob/92ff4caf5302e3779c2050a3857b240dfc16324b/LICENSE)
 Revision 92ff4caf5302
 [Read what was—and wasn’t—checked ↓](#review)

“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.”

 [Traceloop · upstream description ↗](https://github.com/traceloop/opentelemetry-mcp-server/blob/92ff4caf5302e3779c2050a3857b240dfc16324b/README.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - Published in Traceloop's own repository; pyproject.toml at this commit names opentelemetry-mcp with traceloop.com authors and license Apache-2.0, matching the LICENSE file.
- The README's tools table includes get_llm_usage, list_llm_models, get_llm_model_stats, get_llm_expensive_traces and get_llm_slow_traces, which compare models on the token counts and latency an application already records.

### A good fit for

 - Comparing token usage, latency and errors across models from traces your application already sends to Jaeger, Tempo or Traceloop
- Finding failing traces, or the slowest and most token-heavy LLM calls, in a Jaeger, Tempo or Traceloop backend

### Weigh up before choosing

 - The tools report token counts from traces; they do not price tokens. A cost has to be computed separately against current provider rates.
- The README recommends pipx run or uvx, which it says always use the latest version, so the running package is not pinned to this commit.
- Jaeger span search needs a service_name parameter (README backend matrix). The server was not run against any backend.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - README.md at 92ff4caf5302e3779c2050a3857b240dfc16324b
- LICENSE at the same commit
- pyproject.toml at the same commit

### Our findings

 - The README's HTTP mode (--transport http) serves at http://localhost:8000/sse by default; stdio is the mode for Claude Desktop.
- Configuration precedence is CLI arguments, then environment variables (BACKEND_TYPE, BACKEND_URL, BACKEND_API_KEY), then defaults. MAX_TRACES_PER_QUERY defaults to 100.
- pyproject.toml requires Python >=3.11 and declares the opentelemetry-mcp console script.

### Not established by this review

 - pipx or uvx launch
- Any query against Jaeger, Tempo or Traceloop
- The accuracy of token aggregation

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Connect a server deliberately.

[Upstream setup instructions ↗](https://github.com/traceloop/opentelemetry-mcp-server/blob/92ff4caf5302e3779c2050a3857b240dfc16324b/README.md)

DOCUMENTED COMMAND

 pipx run opentelemetry-mcp --backend jaeger --url http://localhost:16686 Copy command ↗

Copying does not execute this command. It may retrieve a newer version than the reviewed source.

 - The README runs the server without installing it, as above, or with uvx. It was not run.
- Set BACKEND_TYPE and BACKEND_URL for your trace backend; Traceloop also needs BACKEND_API_KEY. Do not commit the key.

### Before you start

 - pipx or uv
- Python 3.11 or later
- A Jaeger, Grafana Tempo or Traceloop trace backend

### Documented configuration example

Use the client and authentication context described in the setup guidance. Configuration formats vary between hosts.

 {
 "mcpServers": {
 "opentelemetry-mcp": {
 "command": "pipx",
 "args": [
 "run",
 "opentelemetry-mcp"
 ],
 "env": {
 "BACKEND_TYPE": "jaeger",
 "BACKEND_URL": "http://localhost:16686"
 }
 }
 }
} Copy configuration ↗

### Compatibility

Claude Desktop · Claude Code · Windsurf · Cursor · Gemini CLI

### Implementation

Python

### Transports

stdio · SSE

### Local process reading a trace backend

 - Reads traces and spans from the configured Jaeger, Tempo or Traceloop backend
- Uses BACKEND_API_KEY for Traceloop when set

### Cost model

Apache-2.0 server source. Backend hosting or Traceloop account terms apply; no price was reviewed.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [OpenTelemetry MCP README ↗](https://github.com/traceloop/opentelemetry-mcp-server/blob/92ff4caf5302e3779c2050a3857b240dfc16324b/README.md) Checked 2026-10-13 https://github.com/traceloop/opentelemetry-mcp-server/blob/92ff4caf5302e3779c2050a3857b240dfc16324b/README.md Supports: Supported backends, Tools table, Transports, Configuration
- [OpenTelemetry MCP LICENSE ↗](https://github.com/traceloop/opentelemetry-mcp-server/blob/92ff4caf5302e3779c2050a3857b240dfc16324b/LICENSE) Checked 2026-10-13 https://github.com/traceloop/opentelemetry-mcp-server/blob/92ff4caf5302e3779c2050a3857b240dfc16324b/LICENSE Supports: Apache License 2.0
- [OpenTelemetry MCP pyproject.toml ↗](https://github.com/traceloop/opentelemetry-mcp-server/blob/92ff4caf5302e3779c2050a3857b240dfc16324b/pyproject.toml) Checked 2026-10-13 https://github.com/traceloop/opentelemetry-mcp-server/blob/92ff4caf5302e3779c2050a3857b240dfc16324b/pyproject.toml Supports: Package opentelemetry-mcp, Authors at traceloop.com, License Apache-2.0

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Helicone MCP Server ↗ Connects an assistant to Helicone request logs and sessions, and can send new LLM requests through the Helicone AI Gateway. It runs locally over stdio via the published npm package with a Helicone API key.](/mcp-servers/helicone/)[### MLflow MCP Server ↗ Ships inside the mlflow package and exposes trace search, feedback and assessment logging, and optionally experiment, run, model and deployment commands, to an MCP client.](/mcp-servers/mlflow-mcp/)[### Opik MCP Server ↗ Reads and scores Opik traces, experiments, datasets and prompts from an MCP client. Comet hosts it for Opik Cloud; self-hosted and open-source Opik run the same package locally over stdio.](/mcp-servers/opik-mcp/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Inspect resource evidence](/tools/)
- [Choose a host](/agents/)
- [Inspect reusable workflows](/skills/)
- [Use Undominated data](/api/)
