opik-mcp — security grade SAFE, quality 78/100

Security audit verdict: SAFE · quality 78/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by comet-ml · MCP Server · ★ 217

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is opik-mcp safe to install? View the security audit →

About opik-mcp

opik-mcp Migrating from the old ? The TypeScript server is deprecated and sunsets on 2026-11-15. Swap for in your MCP client config. Full guide: . Model Context Protocol server for Opik + Ollie. Plug your AI host (Claude Code, Cursor, VS Code Copilot, MCP Inspector) directly into your Opik workspace — read traces, log scores, save prompt versions, and ask Ollie investigative questions, all from the chat. Built for LLM engineers who already run Opik and want to drive it from the same AI assistant they code with. Install is a Python package (requires Python 3.13+). The recommended way to run it is , which fetches and runs the latest published version on demand — no global install, no virtualenv juggling. Install once: You'll need two things from your Opik workspace: — get it from [](https://www.comet.com/api/my/settin

claude-codegenerative-aillm-observabilitymcpmcp-servermodel-context-protocolopikpython

Quick Facts

Stars217
Forks35
LanguagePython
CategoryMCP Server
LicenseApache-2.0
Quality Score77.618637887856/100
Open Issues34
Last Updated2026-09-11
Created2025-03-11
Platformsclaude-code, mcp, python
Est. Tokens~18k

opik-mcp alternative? Top 6 similar tools

Looking for a opik-mcp alternative? If you're comparing opik-mcp with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • arcade-mcp by ArcadeAI · ⭐ 1.0k

    MCP Server Framework and Tool Development library for building custom capabilities into agents.

  • drift by dadbodgeoff · ⭐ 785

    Codebase intelligence for AI. Detects patterns & conventions + remembers decisions across sessions. MCP server

  • maverick-mcp by wshobson · ⭐ 657

    MaverickMCP - Personal Stock Analysis MCP Server

  • Overture by SixHq · ⭐ 630

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • roam-code by Cranot · ⭐ 513

    Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 comman

  • mcp-gateway by lasso-security · ⭐ 384

    A plugin-based gateway that orchestrates other MCPs and allows developers to build upon it enterprise-grade ag

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is opik-mcp?

opik-mcp is Model Context Protocol (MCP) server for Opik, the open-source LLM observability and evaluation platform, built by Comet. Read traces, log scores, and manage prompts from Claude Code, Cursor, or VS Cod. It is categorized as a MCP Server with 217 GitHub stars.

What programming language is opik-mcp written in?

opik-mcp is primarily written in Python. It covers topics such as claude-code, generative-ai, llm-observability.

How do I install or use opik-mcp?

You can find installation instructions and usage details in the opik-mcp GitHub repository at github.com/comet-ml/opik-mcp. The project has 217 stars and 35 forks, indicating an active community.

What license does opik-mcp use?

opik-mcp is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to opik-mcp?

The top alternatives to opik-mcp on Agent Skills Hub include arcade-mcp, drift, maverick-mcp. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools