# opik

> MCP Server

Opik is an open-source LLM evaluation framework designed to help build better, faster, and cheaper LLM systems through tracing, evaluations, and dashboards for RAG chatbots, code assistants, and agentic pipelines.

## Overview

- **Category:** AI
- **Language:** Python
- **Stars:** 20939
- **Forks:** 413
- **Owner:** comet-ml
- **GitHub:** https://github.com/comet-ml/opik
- **Homepage:** https://www.comet.com/docs/opik/
- **Created:** 2023-05-10T12:57:13+00:00
- **Updated:** 2025-03-28T22:31:26+00:00
- **Source:** https://model-context-protocol.com/servers/llm-evaluation-tracing-rag-monitoring

## Setup

## Setup
Opik is available as a fully open source local installation or using Comet.com as a hosted solution.
The easiest way to get started with Opik is by creating a free Comet account at [comet.com](https://www.comet.com/signup?from=llm&utm_source=opik&utm_medium=github&utm_content=install&utm_campaign=opik).

If you'd like to self-host Opik, you can do so by cloning the repository and starting the platform using Docker Compose:

On Linux or Mac do:
```bash
# Clone the Opik repository
git clone https://github.com/comet-ml/opik.git

# Navigate to the repository
cd opik

# Start the Opik platform
./opik.sh
```

On Windows do:
```powershell
# Clone the Opik repository
git clone https://github.com/comet-ml/opik.git

# Navigate to the repository
cd opik

# Start the Opik platform
powershell -ExecutionPolicy ByPass -c ".\opik.ps1"
```

Use the `--help` or `--info` options to troubleshoot issues.

Once all is up and running, you can now visit [localhost:5173](http://localhost:5173) on your browser!

For more information about the different deployment options, please see our deployment guides:

| Installation methods | Docs link |
| ------------------- | --------- |
| Local instance | [![Local Deployment](https://img.shields.io/badge/Local%20Deployments-%232496ED?style=flat&logo=docker&logoColor=white)](https://www.comet.com/docs/opik/self-host/local_deployment?from=llm&utm_source=opik&utm_medium=github&utm_content=self_host_link&utm_campaign=opik)
| Kubernetes | [![Kubernetes](https://img.shields.io/badge/Kubernetes-%23326ce5.svg?&logo=kubernetes&logoColor=white)](https://www.comet.com/docs/opik/self-host/kubernetes/#kubernetes-installation?from=llm&utm_source=opik&utm_medium=github&utm_content=kubernetes_link&utm_campaign=opik)


To get started, you will need to first install the Python SDK:

```bash
pip install opik
```

Once the SDK is installed, you can configure it by running the `opik configure` command:

```bash
opik configure
```

This will allow you to configure Opik locally by setting the correct local server address or if you're using the Cloud platform by setting the API Key

## Tools

## Available Tools

1.  Tracing: Track all LLM calls and traces during development and production.
2.  Annotations: Annotate your LLM calls by logging feedback scores using the Python SDK or the UI.
3.  Playground: Try out different prompts and models in the prompt playground.
4.  Datasets and Experiments: Store test cases and run experiments.
5.  LLM as a judge metrics: Use Opik's LLM as a judge metric for complex issues like hallucination detection, moderation and RAG evaluation.
6.  CI/CD integration: Run evaluations as part of your CI/CD pipeline using our PyTest integration.
7.  Log all your production traces: Opik has been designed to support high volumes of traces, making it easy to monitor your production applications.
8.  Monitoring dashboards: Review your feedback scores, trace count and tokens over time in the Opik Dashboard.
9.  Online evaluation metrics: Easily score all your production traces using LLM as a Judge metrics and identify any issues with your production LLM application thanks to Opik's online evaluation metrics.

## Related Articles

- [Mastering opik in 2025](https://model-context-protocol.com/blog/opik-guide)