wx-mp-mcp: 微信小程序逆向 MCP — 在线实时解包 + AI 静态分析还原接口签名/加密,产出本地 Node.js 直接能跑的脚本

by WhiteNightShadow · MCP Server · ★ 232

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

How to install wx-mp-mcp

git clone https://github.com/WhiteNightShadow/wx-mp-mcp.git
claude mcp add wx-mp-mcp -- node /绝对路径/wx-mp-mcp/dist/index.js

Taken from the project's README on GitHub. Check the security audit before running it.

Security audit verdict: SAFE · quality 61/100

None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

Quick Facts

Stars232
Forks39
LanguageJavaScript
CategoryMCP Server
Quality Score61/100
Open Issues1
Last Updated2026-07-29
Created2026-06-29
Platformsmcp, node
Est. Tokens~10k

About wx-mp-mcp

wx-mp-mcp 微信小程序逆向 MCP 把小程序接口的签名 / 加密参数,还原成一个本地 Node.js 就能直接跑的脚本 一个 MCP(Model Context Protocol)Server,装进你的 AI 编码工具(Claude Code / Cursor / Codex),让 AI 自动完成微信小程序的解包 → 抓包 → 签名分析 → 本地复现。  三个核心能力 实时解包 直接读磁盘上的加密包()离线解密成可读 js 源码,主包 / 分包 / 插件全解。微信开不开都行。 数据抓包 HTTPS 代理拦下小程序真实请求,自动存成结构化样本——每条带 url、参数、 签名字段。 AI 离线分析 AI 读 js 定位签名算法 → 穷举反推 / 沙箱实跑复现 → 导出脱离微信的独立签名脚本。 🛡️ 不碰微信进程:全程只做「读磁盘加密包 · 走代理被动抓流量 · Node...

Compatible Skills

These tools work well together with wx-mp-mcp for enhanced workflows:

  • cf-ai-TGbot — semantic(0.40)+complementary+same_lang+similar_pop+shared_platform (64%)
  • claude-code-statusline — semantic(0.27)+complementary+same_lang+similar_pop+shared_platform (60%)

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular JavaScript Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools