Wechat Dev Mcp

Created By
jiawei6864 months ago
This is a Model Context Protocol (MCP) server that connects to WeChat Developer Tools via miniprogram-automator. It allows you to control the IDE and the mini-program from an MCP client (like Claude Desktop or an AI agent).
Overview

WeChat Developer Tools MCP Server

中文

This is a Model Context Protocol (MCP) server that connects to WeChat Developer Tools via miniprogram-automator. It allows you to control the IDE and the mini-program from an MCP client (like Claude Desktop or an AI agent).

Prerequisites

  1. Node.js: Version 18+ is recommended (though it may work on older versions with some polyfills, this project is set up for modern Node).
  2. WeChat Developer Tools: Must be installed and running.
  3. Enable Automation: In WeChat Developer Tools, go to Settings -> Security Settings and enable Service Port (CLI/HTTP invocation).

Quick Start

Add the following to your claude_desktop_config.json (e.g., ~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "wechat-devtools": {
      "command": "npx",
      "args": [
        "-y",
        "wechat-dev-mcp"
      ]
    }
  }
}

Manual Installation

To install globally:

npm install -g wechat-dev-mcp

Then configure:

{
  "mcpServers": {
    "wechat-devtools": {
      "command": "wechat-dev-mcp",
      "args": []
    }
  }
}

Local Development

  1. Clone the repository
  2. Install dependencies:
    npm install
    
  3. Build and run locally:
    node index.js
    
  4. Configure Claude Desktop to point to your local file:
    {
      "mcpServers": {
        "wechat-devtools": {
          "command": "node",
          "args": ["/absolute/path/to/wechat-dev-mcp/index.js"]
        }
      }
    }
    

Available Tools

  • launch: Launch and connect to a mini-program project.
    • projectPath: Absolute path to the project.
    • cliPath: (Optional) Path to the DevTools CLI.
  • connect: Connect to an already running DevTools instance.
    • wsEndpoint: WebSocket endpoint (e.g., ws://localhost:9420).
  • navigate_to: Navigate to a page (e.g., /pages/index/index).
  • get_page_data: Get data from the current page.
  • set_page_data: Set data on the current page.
  • get_element: Get text, attributes, wxml of an element or tap it.
  • call_method: Call a method on the current page instance.
  • disconnect: Disconnect automation.

Troubleshooting

  • Connection Refused: Ensure WeChat Developer Tools is running and the Service Port is enabled in Settings.
  • Path Issues: Use absolute paths for projectPath.

Server Config

{
  "mcpServers": {
    "wechat-devtools": {
      "command": "npx",
      "args": [
        "-y",
        "wechat-dev-mcp"
      ]
    }
  }
}
Project Info
Created At
4 months ago
Updated At
4 months ago
Author Name
jiawei686
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago