经 AI Skill Hub 精选评估,MCP代码审查 获评「推荐使用」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
MCP代码审查 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。
MCP代码审查 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/w1ckedxt/cynical-sally
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"mcp----": {
"command": "npx",
"args": ["-y", "cynical-sally"]
}
}
}
# 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 MCP代码审查 执行以下任务... Claude: [自动调用 MCP代码审查 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": {
"mcp____": {
"command": "npx",
"args": ["-y", "cynical-sally"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <img src="assets/banner.png" alt="Cynical Sally" width="700" /> </p>
<p align="center"> <strong>Brutally honest code reviews. In your terminal and your AI editor.</strong><br/> <em>Because "You're absolutely right" is probably absolutely wrong.</em><br/> <code>npm i -g @cynicalsally/cli</code> · MCP server for Claude Code, Cursor & Windsurf </p>
<p align="center"> <a href="https://cynicalsally.com"><img src="https://cynicalsally.com/api/v1/badge/repo/w1ckedxt/cynicalsally-cli" alt="Cynical Sally Verdict" /></a> <a href="https://cynicalsally.com"><img src="https://img.shields.io/endpoint?url=https%3A%2F%2Fcynicalsally.com%2Fapi%2Fv1%2Fbadge%2Frepo%2Fw1ckedxt%2Fcynicalsally-cli%2Fshields" alt="Sally Score" /></a> <a href="https://www.npmjs.com/package/@cynicalsally/cli"><img src="https://img.shields.io/npm/v/@cynicalsally/cli.svg" alt="npm version" /></a> <a href="https://www.npmjs.com/package/@cynicalsally/cli"><img src="https://img.shields.io/npm/dm/@cynicalsally/cli.svg" alt="npm downloads" /></a> <a href="https://registry.modelcontextprotocol.io/?search=cynicalsally"><img src="https://img.shields.io/badge/MCP-Registry-8a2be2.svg" alt="MCP Registry" /></a> <a href="https://glama.ai/mcp/servers/w1ckedxt/cynical-sally"><img src="https://glama.ai/mcp/servers/w1ckedxt/cynical-sally/badges/score.svg" alt="Glama score" /></a> <a href="https://github.com/w1ckedxt/cynical-sally/blob/main/LICENSE"><img src="https://img.shields.io/github/license/w1ckedxt/cynical-sally.svg" alt="license" /></a> </p>
---
Your AI pair programmer is lying to you. Sally isn't.
<p align="center"> <img src="assets/demo.gif" alt="sally roast — a real review, live in the terminal" width="800" /> </p>
She's the senior engineer your code hoped it'd never meet. Scores from 0 to 10, real issues backed by evidence, and fixes you can actually use.
Works as a CLI tool and as an MCP server in Claude Code, Cursor, and Windsurf.
<p align="center"> <img src="assets/SallyRoast1.png" alt="Sally code review with score and issues" width="500" /> <img src="assets/SallyRoast2.png" alt="Sally actionable fixes and verdict" width="500" /> </p>
sally brainstorm ```
<br clear="right"/>
---
sally review-pr 42
npm install -g @cynicalsally/cli
Or run without installing:
npx @cynicalsally/cli roast ./src/
Requirements: Node.js 18+
```bash
sally roast [paths...] [options]
--staged Review only staged git changes
--diff <branch> Compare against another branch (e.g., main)
-m, --mode <mode> "quick" (default) or "full_truth" (deep dive)
--tone <tone> "cynical" (default), "neutral", or "professional"
--lang <lang> Response language code (default: "en")
--json Output raw JSON (for piping or scripting)
--fail-under <score> Exit code 1 if quality score is below threshold
--ci CI mode: compact output, exit codes
--bg Run Full Truth in background, get OS notification when done
--dry-run Print the exact payload (files, sizes, tokens, SHA-256) and send NOTHING
--card Print + save a shareable roast card after the review
--share Create a public share link (cynicalsally.com/card/…) — score + sneer only, never code
---
<p align="center"> <em>6 tools. Unlimited usage. The most honest code reviewer you'll ever work with — in your terminal and your AI editor.</em> </p>
<p align="center"> <img src="assets/full-suite.png" alt="Sally's Full Suite" width="600" /> </p>
---
Gate your pipeline on code quality:
```yaml
sally roast --diff main
sally review-pr
高质量的MCP代码审查工具
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。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:MCP代码审查 的核心功能完整,质量良好。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | cynical-sally |
| Topics | aiai-code-reviewtypescript |
| GitHub | https://github.com/w1ckedxt/cynical-sally |
| License | MIT |
| 语言 | TypeScript |
收录时间:2026-06-13 · 更新时间:2026-06-13 · License:MIT · 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