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.
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.