WeApp Pilot MCP

English | 简体中文

WeApp Pilot MCP is a local MCP server for LLM and Agent workflows that automate WeChat Mini Programs through WeChat DevTools.

The current public scope focuses on route-aware smoke validation, structured scenario execution, and runtime diagnostics for Taro-based projects.

Highlights

Taro-first project detection and build orchestration
WeChat DevTools plus miniprogram-automator runtime control
Read-only readiness checks with env_check
Active startup validation with preflight_check
Route-aware baseline validation with project_routes, route_search, and smoke_run
Structured step execution with scenario_run
Default-safe redaction for persisted console and network artifacts

Current Scope

local-machine execution
WeChat DevTools must already be installed and logged in
one active runtime session per MCP process
Native Mini Program and UniApp adapters are not implemented yet

Workspace Packages

@weapp-pilot/shared: contracts, error model, and tool schemas
@weapp-pilot/weapp-core: local orchestration, runtime control, assertions, and artifacts
@weapp-pilot/mcp-server: stdio MCP server and tool registry

Workspace Quick Start

pnpm install
pnpm build
pnpm test
pnpm smoke:fixture

pnpm smoke:fixture runs the fake end-to-end validation flow around the bundled Taro fixture and proves that the MCP contracts and runtime orchestration are wired correctly before touching a real WeChat DevTools session.

MCP Client Setup

Use a direct Node entrypoint when wiring the workspace build into an MCP client so stdio is not polluted by package-manager script banners:

{
  "mcpServers": {
    "weapp-pilot": {
      "command": "node",
      "args": ["<repo-root>/packages/mcp-server/dist/bin.js"]
    }
  }
}

The prepared public package name is weapp-pilot-mcp:

npx -y weapp-pilot-mcp

Typical published-package MCP wiring:

{
  "mcpServers": {
    "weapp-pilot": {
      "command": "npx",
      "args": ["-y", "weapp-pilot-mcp"]
    }
  }
}

Recommended Tool Order

env_check
preflight_check
project_routes / route_search
smoke_run
scenario_run

Use smoke_run for baseline route validation and scenario_run only when the external Agent already has a short, explicit step plan.

Documentation

Limitations

The first public path is Taro-first. Native Mini Program and UniApp adapters are planned later.
Runtime automation depends on a prepared local WeChat DevTools environment.
Route discovery is based on compiled Mini Program output such as app.json, so route-aware tools are most reliable after a successful build.
scenario_run is a structured batch executor over existing tools, not a general-purpose planning engine or testing DSL.

License

Apache-2.0

MCP Servers