A set of skills for using Opik to instrument, trace, and evaluate applications built with large language models (LLMs).

It is for adding monitoring and evaluation to LLM applications, including recording their execution traces.

It helps you see what an LLM application did and assess how well it performed.

opik — Plugin for Claude Code by comet-ml/opik-mcp

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/comet-ml/opik-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/comet-ml/opik-mcp/opik/github.svg)](https://agentmods.dev/plugins/comet-ml/opik-mcp/opik)

Your own site

<a href="https://agentmods.dev/plugins/comet-ml/opik-mcp/opik"><img src="https://agentmods.dev/badge/plugins/comet-ml/opik-mcp/opik/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/comet-ml/opik-mcp/opik"><img src="https://agentmods.dev/badge/plugins/comet-ml/opik-mcp/opik.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 10 skills, 1 MCP server cost 1,404 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

opik scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/opik/.claude-plugin/plugin.json · 24 lines

What it actually says

{
  "name": "opik",
  "version": "3.0.8",
  "description": "Opik agent skills and the hosted Opik MCP server: instrument, trace, evaluate and debug LLM applications with Opik.",
  "author": {
    "name": "Comet ML",
    "url": "https://www.comet.com"
  },
  "homepage": "https://www.comet.com/docs/opik/",
  "repository": "https://github.com/comet-ml/opik-mcp",
  "license": "Apache-2.0",
  "keywords": ["opik", "comet", "llm", "observability", "tracing", "evaluation", "mcp", "skills"],
  "documentationUrl": "https://www.comet.com/docs/opik/mcp-server",
  "supportUrl": "https://github.com/comet-ml/opik-mcp/issues",
  "userConfig": {
    "opik_mcp_url": {
      "type": "string",
      "title": "Opik MCP server URL",
      "description": "Keep the default for Opik Cloud. For a self-hosted Opik that serves the MCP server, enter its URL, such as https://<host>/opik/api/v1/mcp.",
      "default": "https://www.comet.com/opik/api/v1/mcp"
    }
  }
}

Contents

What it installs

The manifest is a name and a version. 10 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 1,404 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

marketplace.json 448 B

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

today Changed · +19 lines 0fc3d95ef7c9
1mo ago First seen · 5 lines scan A b726f67d7f39

Subscribe to this mod's changes

opik is a plugin published in the GitHub repository comet-ml/opik-mcp (225 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Analytics and metrics Claude Code Data and AI llm-observability mcp mcp-server model-context-protocol opik

onplana

Connect Gemini CLI + Gemini Code Assist to Onplana. Read and update projects, tasks, sprints, comments, risks, milestones, and team members. Search across your org's indexed content (vector + BM25 RAG). Audited, plan-gated, prompt-injection-contained.

Onplana/onplana-mcp-server · not measured

axon

Axon research, ingestion, retrieval, and operator skills for an existing service.

dinglebear-ai/axon · not measured

cortex

Persistent local-first memory MCP server: remember/recall with thermodynamic heat and decay, knowledge graph, autonomous wiki, local SQLite store by default. Requires uv (uvx) on PATH; hooks-based auto-capture is Claude Code-only — on Gemini CLI memory is manual-tool-driven.

cdeust/Cortex · not measured

opik