Code Review Workflow MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Code Review Workflow MCP Serverreview the code in src/app.js for style issues"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Code Review Workflow — MCP 端到端代码审查流水线
基于 MCP(Model Context Protocol)协议的代码审查工作流,演示如何用标准化协议构建 AI 工具流水线。
架构
用户请求 "检查代码"
│
▼
┌──────────────┐ ┌──────────────────────────┐
│ code_reader │ │ code_checker │
│ MCP Server │ │ MCP Server │
├──────────────┤ ├──────────────────────────┤
│ read_code │ → │ check_style 检查规范 │
│ 读取代码文件 │ │ generate_report 生成报告 │
└──────────────┘ └──────────────────────────┘
│ │
└────────┬───────────────┘
▼
端到端流水线:读文件 → 检查 → 报告Related MCP server: Argus MCP
项目结构
code-review-workflow/
├── shared/ # 共享 MCP 协议栈
│ ├── jsonrpc.js # JSON-RPC 2.0 编解码
│ ├── dispatcher.js # 消息路由
│ ├── framing.js # stdio 字节流分帧
│ ├── session.js # 生命周期状态机
│ ├── registry.js # 工具注册表
│ └── errors.js # 统一错误处理
│
├── code_reader/ # MCP Server 1:代码读取
│ └── server.js
│ └── read_code 接收文件路径 → 返回文件内容
│
├── code_checker/ # MCP Server 2:代码检查
│ └── server.js
│ ├── check_style 接收代码文本 → 检查规范问题
│ └── generate_report 接收检查结果 → 生成格式化报告
│
└── README.md快速开始
环境要求
Node.js 20+
测试 Server 1:code_reader
cd code-review-workflow
node -e "
import { spawn } from 'child_process';
import { createFramer } from './shared/framing.js';
import { encodeRequest, encodeNotification, decode, MessageType } from './shared/jsonrpc.js';
import { Session, PROTOCOL_VERSION } from './shared/session.js';
import { fileURLToPath } from 'url';
// ... (完整测试代码见 examples/end_to_end_test.js)
"检查规则
规则 | 说明 |
console.log 检测 | 生产代码不应保留调试输出 |
TODO/FIXME 检测 | 待完成事项需要跟踪 |
行长检测 | 超过 100 字符的行影响可读性 |
技术栈
协议: MCP (Model Context Protocol) + JSON-RPC 2.0
传输: stdio (stdin/stdout)
运行时: Node.js (纯 JavaScript,零依赖)
协议栈: 基于 mcp-from-scratch 的 6 层架构
面试要点
这个项目展示了:
标准化: 两个 MCP Server 通过统一的 JSON-RPC 协议通信
端到端: 读文件 → 检查规范 → 生成报告,完整流水线
工具开发: 手写 MCP 工具定义(inputSchema)+ 执行函数(handler)
协议理解: 底层掌握 handshake / tools/list / tools/call 全流程
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Checks AI-written code against your rules as it is written, and keeps a record of what it found.
Scan, fix and justify your application code until it is approved to ship.
Screens public GitHub repos and PRs to generate risk maps, findings, and merge-readiness signals.
Lets coding agents check their own code for leaked secrets, risky dependencies and AI-code mistakes
Related MCP Servers
- AlicenseCqualityCmaintenanceProvides access to clean code guide documents and enables code quality inspection of external project files based on coding standards and best practices.34 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI-powered, zero-trust code review with multiple models, supporting single files, git diffs, and multiple files, with security, performance, and architecture checks across 10+ languages.15MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to scan codebases for TODO/FIXME/XXX patterns and get prioritized results over MCP, supporting CI gates and multiple output formats.-
- AlicenseNot gradedqualityDmaintenanceEnables AI-powered code review and improvement, including analysis, refactoring suggestions, and automatic test generation, with an optional agentic loop for iterative refinement.MIT