AI Skill Hub 推荐使用:Opik MCP 是一款优质的MCP工具。AI 综合评分 7.5 分,在同类工具中表现稳健。如果你正在寻找可靠的MCP工具解决方案,这是一个值得深入了解的选择。
Opik MCP 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
Opik MCP 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/comet-ml/opik-mcp
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"opik-mcp": {
"command": "npx",
"args": ["-y", "opik-mcp"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 Opik MCP 执行以下任务... Claude: [自动调用 Opik MCP MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"opik_mcp": {
"command": "npx",
"args": ["-y", "opik-mcp"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
Migrating from the oldnpx opik-mcp? The TypeScript server is deprecated and sunsets on 2026-11-15. Swapnpx -y opik-mcpforuvx opik-mcp@latestin your MCP client config. Full guide:legacy/typescript/MIGRATION.md.
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.
You: "Why did the experiment 'gpt-4o-rerank-v3' regress on factuality?"
Claude: → ask_ollie → reads experiment + traces → "Three traces failed because…"
You: "Score trace 7f2e… 0.9 on helpfulness with reason 'great recovery'."
Claude: → write(score.create) → done
---
opik-mcp is a Python package (requires Python 3.13+). The recommended way to run it is uvx, which fetches and runs the latest published version on demand — no global install, no virtualenv juggling.
Install uv once:
```bash curl -LsSf https://astral.sh/uv/install.sh | sh # macOS / Linux
```
You'll need two things from your Opik workspace:
OPIK_API_KEY — get it from comet.com/api/my/settings/.COMET_WORKSPACE — your workspace name (lowercase, as it appears in the URL). E.g. https://www.comet.com/acme-ai/... → COMET_WORKSPACE=acme-ai. Required for ask_ollie; optional but recommended everywhere else (used for scoping and analytics).Pre-release note:opik-mcp(Python) is not yet published to PyPI. Until the first PyPI release lands, replaceuvx opik-mcpin any snippet below with:uvx --from git+https://github.com/comet-ml/opik-mcp.git opik-mcp
Every setting is an environment variable. Required ones in bold.
| Variable | Default | Notes |
|---|---|---|
**OPIK_API_KEY** | — | Required for ask_ollie and any authenticated read/write. |
**COMET_WORKSPACE** | — | Workspace name. Required for ask_ollie. |
COMET_WORKSPACE_ID | — | Optional workspace UUID. Stamped into analytics events when set so BI can join on a stable id rather than the (mutable) workspace name. |
COMET_URL_OVERRIDE | https://www.comet.com | Set to your self-hosted Comet host, or https://dev.comet.com for staging. |
OPIK_URL | derived from COMET_URL_OVERRIDE + /opik/api | Override only if Opik lives on a different host/path than the Comet UI. |
OPIK_DEFAULT_PROJECT_NAME | _unset_ | When set, the per-session instructions blob tells the LLM to pass this as project_name on every tool call unless the user names a different project. |
.vscode/mcp.json in your workspace (or User Settings JSON):
{
"servers": {
"opik-mcp": {
"type": "stdio",
"command": "uvx",
"args": ["opik-mcp"],
"env": {
"OPIK_API_KEY": "<your-key>",
"COMET_WORKSPACE": "<your-workspace>"
}
}
}
}
Reload the window; the Copilot Chat MCP indicator shows opik-mcp once the server is reachable. Ask in chat: "list my Opik projects".
OPIK_API_KEY is required to use ask_ollie — the var isn't reaching the server process. In Claude Code / Cursor / VS Code, env vars only apply when inside the env block of the MCP server config, not your shell. Restart the host after editing.
ask_ollie returns "pod not ready" after 2 minutes — the Ollie pod cold-start exceeded OPIK_MCP_POD_READY_TIMEOUT_S. Retry — the second call usually hits a warm pod.
ask_ollie / run_experiment fails with a dispatch error on self-hosted Opik — those tools are available on Comet Cloud only. Use read / list / write directly on self-hosted.
Cursor call times out at 60s — Cursor's known bug, not opik-mcp. Either shorten the Ollie query, or run the same operation on Claude Code which has no hard cap.
---
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
总体来看,Opik MCP 是一款质量良好的MCP工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | opik-mcp |
| 原始描述 | 开源MCP工具:Model Context Protocol (MCP) implementation for Opik enabling seamless IDE integ。⭐205 · Python |
| Topics | mcpgenerative-aipython |
| GitHub | https://github.com/comet-ml/opik-mcp |
| License | Apache-2.0 |
| 语言 | Python |
收录时间:2026-05-28 · 更新时间:2026-05-28 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端