spec-guard
A deterministic MCP server that checks project code alignment with SPEC documents through static analysis without AI involvement.
README
<h1 align="center">spec-guard</h1> <p align="center"><strong>SPEC 与代码对齐检查 MCP · 自建确定性检查,无 AI 参与</strong></p> <p align="center"> <img src="https://img.shields.io/badge/license-MIT-blue.svg" alt="License: MIT"> <img src="https://img.shields.io/badge/TypeScript-5.0-3178C6" alt="TypeScript"> <img src="https://img.shields.io/badge/protocol-MCP-7B3FE4" alt="MCP"> </p>
spec-guard 是一个确定性 MCP(Model Context Protocol)服务器,用于检查项目代码是否与 SPEC 文档保持一致。它不依赖 AI 判断,纯静态分析,结果可复现。
核心能力
| 工具 | 检查项 | 准确度 | 说明 |
|---|---|---|---|
spec_check_interfaces |
API 端点 | ~99% | SPEC 中定义的端点是否都在代码中实现 |
spec_check_models |
数据模型字段 | ~98% | 实体字段名与代码中的字段是否匹配 |
spec_check_security |
安全措施 | ~80-90% | 安全需求(限流/JWT/加密等)是否在代码中落地 |
spec_check_env |
环境变量 | ~98% | SPEC 声明的环境变量是否在代码中使用 |
快速开始
前置条件
- Node.js 18+
- npm
安装与运行
# 克隆
git clone https://github.com/loongarch-pirun/spec-guard.git
cd spec-guard
# 安装依赖
npm install
# 构建
npm run build
# 运行(标准输入输出模式,供 MCP 客户端使用)
node dist/server.js
# 开发模式(热重载)
npm run dev
MCP 客户端配置
在 MCP 客户端中添加:
{
"mcpServers": {
"spec-guard": {
"command": "node",
"args": ["path/to/spec-guard/dist/server.js"]
}
}
}
参数说明
所有工具使用相同的参数:
| 参数 | 类型 | 必填 | 说明 |
|---|---|---|---|
specPath |
string | ✅ | SPEC.md 文件的路径 |
codeDir |
string | ✅ | 项目代码目录路径 |
返回格式
{
"tool": "spec_check_interfaces",
"grade": "PASS | WARN | FAIL",
"accuracy": "~99%",
"checks": [
{ "path": "GET /api/users", "ok": true, "location": "routes/users.ts:42" },
{ "path": "POST /api/login", "ok": false, "detail": "not found" }
]
}
项目结构
spec-guard/
├── src/
│ ├── server.ts # MCP 服务器入口 & 检查逻辑
│ └── utils/
│ ├── parse-spec.ts # SPEC 文档解析器
│ └── scan-code.ts # 代码扫描器
├── package.json
├── tsconfig.json
├── README.md
├── LICENSE
└── .github/
├── ISSUE_TEMPLATE.md
└── PULL_REQUEST_TEMPLATE.md
与 hua-think-lite 配合使用
spec-guard 与 hua-think-lite 形成三阶段代码门禁:
写代码前 写代码时 代码完成后
┌──────────────┐ ┌──────────────┐ ┌──────────────┐
│ hua-think │ → │ hua-think │ → │ spec-guard │
│ guard_validate│ │ guard_check │ │ spec_check_* │
│ 符号验证 │ │ 路径安全审查 │ │ SPEC一致性 │
└──────────────┘ └──────────────┘ └──────────────┘
贡献
欢迎贡献!请阅读 CONTRIBUTING.md。
许可证
MIT — 详见 LICENSE。
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.