production-master
Enables triggering, streaming, and reviewing autonomous production-incident investigations directly from your editor, with human-gated approval for any mutating actions.
README
<p align="center"><img src="assets/banner.svg" alt="production-master" width="600" /></p>
<p align="center"> <a href="https://github.com/ProductionMasterAI/production-master/actions/workflows/ci.yml"><img src="https://github.com/ProductionMasterAI/production-master/actions/workflows/ci.yml/badge.svg" alt="CI" /></a> <a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-blue.svg" alt="License: MIT" /></a> <a href="https://claude.ai/code"><img src="https://img.shields.io/badge/Claude_Code-plugin-D97757?logo=anthropic&logoColor=white" alt="Claude Code plugin" /></a> <a href="https://github.com/ProductionMasterAI"><img src="https://img.shields.io/badge/author-ProductionMasterAI-181717?logo=github&logoColor=white" alt="Author" /></a> <a href="CHANGELOG.md"><img src="https://img.shields.io/badge/version-0.1.0-blue" alt="Version" /></a> </p>
<p align="center"> <img src="https://img.shields.io/badge/Claude%20Code-pending-lightgrey" alt="Claude Code: validation pending" /> <img src="https://img.shields.io/badge/Cursor-pending-lightgrey" alt="Cursor: validation pending" /> <img src="https://img.shields.io/badge/Codex-pending-lightgrey" alt="Codex: validation pending" /> <img src="https://img.shields.io/badge/OpenCode-pending-lightgrey" alt="OpenCode: validation pending" /> </p>
Trigger, stream, and review autonomous production-incident investigations without leaving your editor.
Production Master is a thin client for the Production Master hosted service. You point it at an incident, it starts an investigation on the service, and the results stream back into your IDE in real time. When the investigation proposes an action that changes something, you approve or reject it — nothing runs without your sign-off.
The investigation itself runs entirely on the hosted service. This repository is the thin client: it handles device-code login, starts a run, streams live progress, renders the report, and relays your approve/reject decisions. No investigation logic, model provider SDKs, or credentials for the analysis live here.
Features
- IDE-native investigations — start and follow a run from Claude Code, Cursor, Codex, or OpenCode. No context switch to a separate dashboard.
- Live streaming — progress, findings, and the final report stream over Server-Sent Events (SSE) as the hosted service works.
- Human-gated actions — every proposed action that mutates a system is surfaced for explicit approval; you approve or reject before anything happens.
- Multi-IDE support — one thin client, registered through each editor's native extension mechanism (plugin, MCP config, or config file).
Prerequisites
- Node.js 22 (see
.nvmrconce packages land) - An account on the Production Master hosted service — the client authenticates to it via device-code login.
- One of the supported editors: Claude Code, Cursor, Codex, or OpenCode.
Quick Start
Status: the client packages under
packages/are being populated via PRs. The install steps below describe the registration pattern each IDE uses; the concrete manifest for your editor lands with those PRs. See CHANGELOG.
Across every editor the flow is the same: register the client → log in with a device code → start an investigation.
Claude Code
Install as a plugin, then log in:
/plugin install production-master
/login
Cursor
Register the client as an MCP server in .cursor/mcp.json:
{
"mcpServers": {
"production-master": {
"command": "npx",
"args": ["-y", "@production-master/client"]
}
}
}
Codex
Register the client in .codex/config.toml:
[mcp_servers.production-master]
command = "npx"
args = ["-y", "@production-master/client"]
OpenCode
Register the client in opencode.json:
{
"mcp": {
"production-master": {
"command": ["npx", "-y", "@production-master/client"]
}
}
}
After registering, run the login command to authenticate against the hosted service, then start your first investigation. Full walkthrough: docs/user/quick-start.md.
Architecture
The client is a thin transport-and-render layer. All investigation logic lives on the hosted service; the client talks to it over HTTPS (control) and SSE (streaming).
flowchart LR
subgraph IDE["Your IDE"]
C["production-master<br/>thin client"]
end
S["Production Master<br/>hosted service"]
C -- "device-code login (HTTPS)" --> S
C -- "start / approve / reject (HTTPS)" --> S
S -- "live progress + report (SSE)" --> C
The client owns four concerns: auth (device-code login + token storage), MCP transport (exposing thin-client commands to the editor), streaming (consuming SSE and rendering progress), and render adapters (per-IDE presentation). It owns none of the analysis. See docs/engineering/architecture/overview.md.
Documentation
| Doc | Purpose |
|---|---|
| Quick Start | Install, log in, run your first investigation |
| Usage | Common workflows — start, connect, approve/reject |
| Commands | Thin-client command reference |
| Troubleshooting | Auth, service URL, and MCP registration issues |
| Architecture | Thin-client components and data flow |
| ADR-001 | Thin client over hosted service |
| Contributing | How to contribute |
| Changelog | Release history |
License
MIT — see LICENSE.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。