WeChat DevTools Bridge
Connects WeChat Mini Program tooling to MCP and automation workflows. Provides scripts for opening, previewing, and uploading projects, as well as automator smoke tests.
README
WeChat DevTools Bridge
An open-source Codex plugin that connects WeChat Mini Program tooling to MCP and automation workflows.
What it does
- Provides a local Codex plugin manifest
- Ships an MCP configuration for Windows
- Adds helper scripts to locate WeChat DevTools and check prerequisites
- Provides executable wrappers for open, preview, upload, and automator smoke tests
Current approach
This plugin uses official WeChat-adjacent tooling for the executable path and keeps MCP pluggable.
That gives us a practical bridge for:
- checking WeChat DevTools availability
- connecting Codex to local Mini Program tooling
- opening, previewing, and uploading projects
- validating automator connectivity
Prerequisites
- Windows PowerShell
- Node.js 16+
- nvm for Windows is supported
- WeChat DevTools installed
- WeChat DevTools service port enabled
Files
.codex-plugin/plugin.json: Codex plugin manifest.mcp.json: MCP server wiringscripts/check-prereqs.ps1: local environment checkscripts/find-wechat-devtools.ps1: locate a likely DevTools CLI pathscripts/invoke-weapp-cli.ps1: shared wrapper aroundweapp-ide-cliscripts/open-project.ps1: open the current project in WeChat DevToolsscripts/preview-project.ps1: run a preview flowscripts/upload-project.ps1: run an upload flowscripts/start-weapp-devtools-mcp.ps1: launches a configurable MCP packagescripts/automator-smoke.cjs: validatesminiprogram-automatorconnectivitypackage.json: npm dependencies and convenience scripts
Quick start
- Open WeChat DevTools and enable the service port in security settings.
- Run:
./scripts/check-prereqs.ps1
- If needed, set the CLI path explicitly:
$env:WECHAT_DEVTOOLS_CLI = "C:\\Path\\To\\WeChatDevTools\\cli.bat"
- Start the MCP bridge manually:
./scripts/start-weapp-devtools-mcp.ps1
- Open the current mini program project:
./scripts/open-project.ps1
- Run an automator smoke test after DevTools is exposing the websocket endpoint:
$env:WECHAT_WS_ENDPOINT = "ws://127.0.0.1:9420"
npm run automator:smoke
npm scripts
npm install
npm run check
npm run devtools:open
npm run devtools:preview
npm run automator:smoke
devtools:upload requires additional arguments, for example:
./scripts/upload-project.ps1 -Version 0.1.0 -Desc "Initial upload"
Environment variables
WECHAT_DEVTOOLS_CLI: explicit path to the DevTools CLIWECHAT_PROJECT_PATH: mini program project rootWECHAT_WS_ENDPOINT: automator websocket endpoint, defaultws://127.0.0.1:9420WECHAT_MCP_NPX_PACKAGE: optional community MCP package name used bystart-weapp-devtools-mcp.ps1WECHAT_NODE_EXE: optional explicitnode.exeoverrideWECHAT_NPX_CMD: optional explicitnpx.cmdoverride
nvm for Windows
If you use nvm for Windows, the scripts now try:
WECHAT_NODE_EXE/WECHAT_NPX_CMD- the current shell
node/npx NVM_SYMLINK\\node.exeandNVM_SYMLINK\\npx.cmdNVM_HOME\\<current-version>\\node.exeandnpx.cmdwhenNVM_CURRENTis setC:\\Program Files\\nodejs\\node.exeandnpx.cmd
If your environment still does not resolve Node correctly, run nvm use <version> first or set the explicit overrides above.
MCP config
The bundled .mcp.json uses:
{
"mcpServers": {
"wechat-devtools-bridge": {
"command": "powershell.exe",
"args": [
"-NoProfile",
"-ExecutionPolicy",
"Bypass",
"-File",
"./scripts/start-weapp-devtools-mcp.ps1"
]
}
}
}
Recommended toolchain
weapp-ide-cli: open / preview / upload wrappers around the WeChat DevTools CLIminiprogram-automator: websocket-based DevTools automation checks- a community WeChat DevTools MCP package of your choice, passed via
WECHAT_MCP_NPX_PACKAGE
Upstream references
miniprogram-automator: https://www.npmjs.com/package/miniprogram-automatorweapp-ide-cli: https://www.npmjs.com/package/weapp-ide-cli- community MCP example: https://glama.ai/mcp/servers/%40yfmeii/weapp-dev-mcp
Notes
- The helper scripts are intentionally conservative and Windows-first.
- The repository keeps the MCP backend configurable because community MCP packages evolve quickly.
- If you want a pure Node launch path later, we can add one.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。