💡 Summary
UniAPP AI Tools provides a setup for integrating MCP with UniApp for enhanced development.
🎯 Target Audience
🤖 AI Roast: “The README suggests network access to a local MCP server, which could expose sensitive data if not secured. Ensure proper firewall rules and access controls are in place.”
Risk: Medium. Review: shell/CLI command execution; outbound network access (SSRF, data egress); dependency pinning and supply-chain risk. Run with least privilege and audit before enabling in production.
[WIP]UniAPP AI Tools
缓慢随缘更新中,欢迎贡献你的 uniapp 最佳实践来完善 skills。
仅使用 MCP 即可按下方文档安装。使用
MCP + RAG方案来查询 uniapp 文档。
安装
pnpm add @uni-helper/mcp -D
配置
在 vite.config.ts 中添加如下配置:
import mcp from '@uni-helper/mcp' import uni from '@uni-helper/plugin-uni' import { defineConfig } from 'vite' export default defineConfig({ plugins: [uni(), mcp()], })
配置 MCP 服务器
{ "mcpServers": { "uni": { "url": "http://localhost:2515/mcp" } } }
注意如果使用pnpm,请在pnpm-workspace.yaml中添加如下配置:
确保能正确构建@uni-helper/mcp插件
onlyBuiltDependencies: - hnswlib-node - '@uni-helper/mcp'
Pros
- Easy integration with UniApp.
- Supports modern development practices.
- Encourages community contributions.
Cons
- Still a work in progress.
- Limited documentation.
- Dependency on specific tools.
Related Skills
web-perf
A“This skill is so thorough it might start charging consulting fees after the audit.”
tldraw
A“A fantastic library for drawing, though its licensing model means your masterpiece will forever be signed 'Made with tldraw' unless you pay the ransom.”
Disclaimer: This content is sourced from GitHub open source projects for display and rating purposes only.
Copyright belongs to the original author uni-helper.
