Advertise
MCP.so
Sign In

Wechat Dev MCP Server

@jiawei686

Repository

Basic information

Category

AI & Agents

License

MIT

Transports

stdio

Author

jiawei686

Submitted by

Felix CUI

About Wechat Dev MCP Server

mcp server for wechat dev tools

#wechat#dev#miniprogram#minigame

Wechat Dev MCP Server config

Add this server to your MCP-compatible client using the configuration below.

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

Wechat Dev MCP Server tools

9

Launch and connect to WeChat Developer Tools. [REQUIRED INITIAL STEP] Use this tool first to start controlling a mini-program. Requires the absolute project path.

Connect to an already running WeChat Developer Tools instance via WebSocket. Use this if 'launch' fails or you want to attach to an existing session.

[CRITICAL] Use this tool to verify if the mini-program is running correctly after ANY code changes. It returns the current page path, network status, and recent console errors.

Navigate to a specific page in the mini-program.

Get the data of the current page. Useful for verifying state changes after interactions or API calls.

Set data on the current page. Use this to mock state or trigger UI updates for testing.

Get information about an element (text, wxml, attributes, computed style) or interact with it (tap, input, trigger). Use this to inspect UI or perform actions.

Call a method on the current page.

Disconnect from the mini-program.

Overview

What is Wechat Dev Mcp?

It controls WeChat Developer Tools and mini‑programs/mini‑games via the Model Context Protocol (MCP). It works with Claude Desktop, Cursor, Windsurf, and any MCP-compatible AI agent.

How to use Wechat Dev Mcp?

Install Node.js v18+ and enable the Service Port in WeChat DevTools (设置 → 安全设置 → 服务端口). Add the server configuration (using npx -y wechat-dev-mcp or a globally installed wechat-dev-mcp command) to your MCP client’s settings. Then use the provided tools to launch, connect, and automate DevTools.

Key features of Wechat Dev Mcp

  • 36 tools covering connection, navigation, and interaction
  • Automated launch and WebSocket connection to DevTools
  • Element interaction: tap, long-press, input text
  • Code execution: evaluate JavaScript and call wx.* APIs
  • Mini‑game specific tools (info, user info, cloud storage)
  • Debugging: console logs, screenshots, health checks

Use cases of Wechat Dev Mcp

  • Debug and test mini‑program pages (state, UI, navigation)
  • Automate repetitive DevTools operations (build npm, deploy cloud functions)
  • Interact with mini‑games: run scripts, call APIs, check logs
  • Integrate WeChat DevTools into CI/CD or AI‑assisted workflows
  • Verify code changes with health checks after each modification

Frequently asked questions

1

What prerequisites are needed?

Node.js v18+, WeChat DevTools installed with the Service Port enabled, and an open mini‑program or mini‑game project.

2

How do I connect to a running DevTools instance?

Use the `launch` tool (opens DevTools and a project) or the `connect` tool (connects via WebSocket, default `ws://localhost:9420`).

3

What should I do if I get a "Connection refused" error?

Ensure DevTools is running and the Service Port is enabled in the settings. Then retry the connection.

4

Can I use page tools (e.g., `get_element`) on a mini‑game?

No. Page tools return clear errors if used on a game project. Use `evaluate`, `call_wx_method`, or the `game_*` tools instead.

5

How can I verify everything works after making code changes?

Run the `check_health` tool. It checks connection, page path, network, console errors, and project type.

Comments

More AI & Agents MCP servers

OpenZiti / LLM-Gateway

openziti

NetFoundry LLM Gateway is an OpenAI-compatible API proxy that routes requests across multiple LLM providers using zero-trust networking. Zero trust LLM gateway. OpenAI-compatible proxy with semantic routing and load bala

93

GoBuy - Product Trust

gobuy-ai

GoBuy gives AI agents marketplace-evidence trust scores. One call returns a 0–100 Evidence Score with observed/missing signals, freshness, and product context. Tools: • check_product_trust — inspect one Amazon, Walmart,

scvd.store

seancrecord

scvd.store is an evidence observatory for agentic commerce. Independent signed observation of what other people's endpoints, artifacts and payments actually did among other things. USDC on Base, Arbitrum One, World Chain

2

strac-mcp-dlp

strac-io

Detect and redact PII, PHI, PCI and secrets — SSNs, credit cards, passports, API keys and cloud credentials — in text and in local files, using the Strac DLP API. Five tools: redact_text, detect_sensitive_data, detect_fi

3

Phi Longevity PRISM

Phi Longevity

Guideline-cited lab-results analysis for people managing type 2 diabetes, kidney disease, lupus and cancer survivorship. Flags tests that are missing or overdue (ADA, KDIGO, NCCN — each cited) and returns questions to br

Advertise