Code Review Workflow MCP Server
Enables automated code review by reading code files, checking for style issues like console.log and TODOs, and generating formatted reports.
README
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
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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.