weapp-agent-mcp
Agent-first MCP server for WeChat Mini Program debugging & automation via WeChat DevTools.
Open the source (opens github.com) https://github.com/chaixueyuan/weapp-agent-mcp
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
- Needs credentials: WEAPP_AUTO_ACCOUNT, WEAPP_DEVTOOLS_TICKET. Use a key with the least access you can.
What it is
MCP servers from io.github.Chaixueyuan.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
npm package (stdio)
@chaixueyuan/weapp-agent-mcp@0.4.8
From the server's entry in the official MCP Registry
Settings it asks for
WEAPP_WS_ENDPOINT· Automation WebSocket endpoint for the 'connect' flow (e.g. ws://localhost:9420). When a local endpoint is not listening and auto-launch is enabled…WEAPP_AUTOMATOR_MODE· Force 'launch' or 'connect' mode. Defaults to 'launch' unless WEAPP_WS_ENDPOINT is set.WEAPP_PROJECT_PATH· Optional Mini Program project directory used by launch and local auto-launch flows. The server can also resolve a persisted default, a recent project, or the…WECHAT_DEVTOOLS_CLI_PATH· Optional override for the WeChat DevTools CLI binary path (e.g. /Applications/wechatwebdevtools.app/Contents/MacOS/cli on macOS).WEAPP_DEVTOOLS_PORT· Automation websocket port passed to 'cli auto --auto-port' in launch mode (default 9420).WEAPP_DEVTOOLS_TIMEOUT· Milliseconds passed to miniprogram-automator when launching WeChat DevTools.WEAPP_AUTO_ACCOUNTsecret · Optional account passed to miniprogram-automator launch.WEAPP_DEVTOOLS_TICKETsecret · Optional DevTools launch ticket.WEAPP_TRUST_PROJECT· Whether launch mode should trust the project. Accepts true/false, 1/0, yes/no, or on/off.WEAPP_DEVTOOLS_ARGS· Additional whitespace-separated CLI arguments passed during launch.WEAPP_DEVTOOLS_CWD· Optional working directory passed to the DevTools launch process.WEAPP_AUTOCLOSE· Whether to close or disconnect the automator session after each tool call. Accepts true/false, 1/0, yes/no, or on/off.
Related
-
GitHub MCP server
MCP serversGitHub's official MCP server. It lets an agent read and work with repositories, issues and pull requests.
https://api.githubcopilot.com/mcp/ -
Apify MCP server
MCP serversLets an agent run Apify's ready-made scrapers to pull data from websites, search engines, maps and social platforms.
-
Official MCP Registry
MCP serversThe MCP project's own registry of public MCP servers, so you can look for a connector before building one.
-
MCP reference servers
MCP serversSmall example servers from the MCP project (filesystem, git, fetch, memory and more) that show how MCP works.
-
Connect MCP servers to Claude Code
MCP serversAnthropic's guide to adding MCP servers to Claude Code, with examples of local and remote servers.
-
Playwright MCP
MCP serversLets an agent drive a real browser: open pages, click, fill in forms and read what's on screen.
claude mcp add playwright npx @playwright/mcp@latest