Weapp Dev MCP
The WeChat Mini Program Automated Testing MCP Server realizes automated control of the WeChat Developer Tools through FastMCP and miniprogram - automator, providing a toolset for page navigation, element operation, API calls, etc.
rating : 2.5 points
downloads : 5.6K
What is the WeChat Mini Program MCP Server?
It is a bridge connecting AI assistants with the WeChat Developer Tools. It allows AI (such as Claude) to automatically control the WeChat Developer Tools through simple instructions, enabling page navigation, element operation, data viewing, and function testing of mini-programs. Similar to an automated testing tool customized for WeChat mini-programs, but driven by AI.How to use the WeChat Mini Program MCP Server?
First, you need to install the WeChat Developer Tools on your computer and enable the automated service port. Then, configure and start this server through a client that supports MCP, such as Claude Desktop. The AI assistant can then perform automated operations on the specified mini-program project through the provided toolset.Applicable Scenarios
Suitable for mini-program developers to conduct rapid function demonstrations, UI inspections, data state verifications, automated test script generation, or to complete repetitive page operation tasks with the assistance of AI.Main Features
Automated Connection Management
Intelligently connect to the WeChat Developer Tools, support starting via the command line or connecting to an existing WebSocket service, and configure parameters such as timeout and port.
Mini-program Page Navigation
Support various navigation methods within the mini-program, such as jumping to a new page, redirecting, switching the Tab bar, and returning to the previous page.
Page and Element Inspection
Get the page structure (WXML), page data, and console logs, and locate and query specific elements on the page through selectors.
Simulate User Interaction
Simulate user operations such as clicking and entering text, and call the native APIs of the mini-program (such as displaying pop - ups) or methods defined within the page/component.
Custom Component Operation
Specifically support operations on custom components of the mini-program, including calling component methods and getting and setting internal component data.
Screenshot
Capture a screenshot of the current page of the mini-program for visual verification of the page state.
Advantages
Customized for the WeChat mini-program ecosystem, the toolset better meets the actual needs of developers.
No need to write code. Automated operations can be driven through natural language instructions, reducing the usage threshold.
Support flexible connection modes and can be integrated into the existing development workflow.
Provide rich tools covering core testing scenarios such as navigation, inspection, and interaction.
Limitations
Depends on the locally installed WeChat Developer Tools and cannot be operated remotely.
Some advanced automation capabilities are limited by the support of the WeChat Developer Tools itself.
When operating internal elements of custom components, there are limitations with some tools (such as waiting for elements).
Requires correct configuration of environment variables and developer tool settings, and there are certain steps in the initial setup.
How to Use
Environment Preparation
Ensure that Node.js (18+), npm, and the WeChat Developer Tools are installed on your computer, and you have a mini-program project that can be opened.
Configure the Developer Tools
Open the WeChat Developer Tools, go to [Settings → Security Settings → Service Port], and enable the 'HTTP Debugging' and 'Automated Testing' functions.
Start the Developer Tools Service
Start the developer tools through the command line and enable the WebSocket service, specifying the path to your mini-program project.
Configure the MCP Client
In the configuration file of clients such as Claude Desktop, add the startup command and environment variables of the weapp - dev - mcp server.
Start Collaborating with AI
Restart the client, and the AI assistant can use the MCP tools to perform automated operations on your mini-program. You can first try to let the AI establish a connection.
Usage Examples
Example 1: Quickly Check Page Data
The developer wants to confirm whether the data is correctly rendered after a page is loaded.
Example 2: Simulate the Login Process
Test whether the login function of the mini-program is working properly.
Example 3: Debug Custom Components
A custom product card component developed by the developer is showing abnormal behavior, and the internal state needs to be checked.
Frequently Asked Questions
What should I do if I encounter the error 'Server does not support completions' when starting?
Why can't the AI operate the buttons inside the custom components on my page?
Do I have to start the WeChat Developer Tools through the command line?
How should I write the path when navigating pages?
Can this tool be used for real - device debugging or code uploading?
Related Resources
Official Documentation of miniprogram - automator
The official description of the WeChat mini - program automation tool library on which this project depends.
Official Website of Model Context Protocol (MCP)
The official site to learn about the MCP protocol, including protocol specifications and introductions.
Download the WeChat Developer Tools
Download the latest version of the WeChat Developer Tools.
npm Package Page
The official npm page of this MCP server package, where you can view version information.

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
17.5K
4.3 points

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
27.6K
5 points

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
17.6K
4.5 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
54.2K
4.3 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
24.3K
5 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
52.4K
4.5 points

Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
17.2K
4.5 points

Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
76.7K
4.7 points

