tcsas-devtools-mcp-server
Enables AI assistants to manage TCSAS miniprogram development tasks such as launching the IDE, previewing, and uploading miniprograms via natural language.
README
TCSAS-Devtools MCP Server
An MCP (Model Context Protocol) server designed to connect AI assistants with TCSAS-Devtools for a seamless miniprogram development experience.
This server wraps the basic functionalities of TCSAS-Devtools into a set of tools that can be called by AI assistants (like CodeBuddy, Cursor, Claude), allowing you to open, build, preview, and upload miniprograms using natural language.
✨ Features
- Launch IDE: Directly open the
TCSAS-Devtoolsapplication or a specific miniprogram project. - Check Installation: Verify if
TCSAS-Devtoolsis installed on the local machine. - Preview Miniprogram: Generate a QR code for previewing the miniprogram on a mobile device.
- Upload Miniprogram: Upload a new version of the miniprogram with specified version information.
🚀 Prerequisites
Before you begin, ensure you have the following software installed:
- Node.js (v20 or higher recommended)
- npm
- TCSAS-Devtools
📦 Installation and Setup
- For first-time use, please download the installation package for TCSAS-Devtools from the console in advance, the version should >= 2.2.15.
- After installation, please open it to complete the login process and enable the service port.
Settings - Security - Enable

Ensure the above steps are completed. Then you can configure the MCP server in your Code Agent and start using it.
🤖 How to Use in Cursor
You can integrate this server with any AI assistant that supports custom MCP servers. Here are the steps to configure it in Cursor:
-
Open Cursor Settings: In Cursor, find the settings for AI integration. This is usually located in
Settings>Tools & MCPor a similar configuration area for managing AI providers. -
Add Custom MCP Service: Look for an option like "Add Model Context Provider" or "MCP Server" and click "Add".
-
Enter Command: For example:
{ "tcsas-devtools-mcp-server": { "command": "npx", "args": [ "-y", "tcsas-devtools-mcp-server@latest" ] } }Illustration: (A screenshot of the Cursor settings panel could be like this, showing the user entering the command in the mcp.json)

-
Connect and Start Using: After adding, Cursor will connect to your local server. Now you can interact with it in the chat. For example, you can type:
"Launch TCSAS-Devtools and open my project at
/Users/me/projects/my-miniprogram.""Generate a preview QR code for the project I'm currently developing."
🛠️ Tool API Reference
Below is a detailed description of all the tools provided by this MCP server:
launchIde
Launches the TCSAS-Devtools IDE.
- Input Parameters:
path(optional, string): The absolute path to the miniprogram project to open.
checkIdeInstalled
Checks if the TCSAS-Devtools IDE is installed.
- Input Parameters: None
previewMiniprogram
Generates a preview QR code for a miniprogram project.
- Input Parameters:
path(string): The absolute path to the miniprogram project.
uploadMiniprogram
Uploads a new version of the miniprogram.
- Input Parameters:
path(string): The absolute path to the project.version(string): The new version number (e.g., "1.0.1").describeMessage(string): A short description of the changes.
Contributions are welcome! Please feel free to submit a Pull Request.
📜 License
This project is open-sourced under the MIT License.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.