README-EN.md

CloudBase MCP

🪐 Go from AI prompt to live app in one click
The bridge that connects your AI IDE (Cursor, Copilot, etc.) directly to Tencent CloudBase

Languages: 中文 | English · Documentation · Changelog · Report Issues

Found a game-changer for AI coding: one-click deploy from prompt to production

^{The shortest path from AI prompt to live application}

Why You Need CloudBase MCP

AI programming tools (like Cursor, Copilot) solve the code generation challenge.

However, there's still a gap between "generating code" and "application going live" (deployment, database configuration, CDN, domain setup).

CloudBase MCP (formerly CloudBase AI ToolKit) bridges this gap.

You no longer need:

• ❌ Complex DevOps configuration and YAML files
• ❌ Manual setup of cloud functions and databases
• ❌ Switching back and forth between IDE and cloud console

You only need to use natural language in your AI IDE to complete the entire journey from "idea" to "live".

Table of Contents

• Quick Start
• Core Features
• Installation & Configuration
• Use Cases
• MCP Tools
• More Resources

Quick Start

One-Line Configuration, Start Using Immediately

In AI IDEs that support MCP (Cursor, WindSurf, CodeBuddy, etc.), just add one line of configuration:

{
  "mcpServers": {
    "cloudbase": {
      "command": "npx",
      "args": ["@cloudbase/cloudbase-mcp@latest"]
    }
  }
}

Tip

Recommended: CloudBase AI CLI

One-click installation, automatic configuration, supports multiple AI programming tools:

npm install @cloudbase/cli@latest -g

After installation, run tcb ai to start using

View complete documentation | Detailed case tutorial

First Time Use

1. Login to CloudBase

   Login to CloudBase
   

   AI will automatically open the login interface and guide environment selection

2. Start Developing

   Build a two-player online Gomoku game website, support online battle, and deploy it
   

   AI will automatically generate code, deploy to the cloud, and return the access link

Supported AI IDEs

Tool	Supported Platform	Guide
CloudBase AI CLI	CLI	Guide
Cursor	Standalone IDE	Guide
WindSurf	Standalone IDE, VSCode, JetBrains Plugin	Guide
CodeBuddy	Standalone IDE (CloudBase built-in), VS Code, JetBrains, WeChat DevTools	Guide
CLINE	VS Code Plugin	Guide
GitHub Copilot	VS Code Plugin	Guide
Trae	Standalone IDE	Guide
Tongyi Lingma	Standalone IDE, VS Code, JetBrains Plugin	Guide
RooCode	VS Code Plugin	Guide
Baidu Comate	VS Code, JetBrains Plugin	Guide
Augment Code	VS Code, JetBrains Plugin	Guide
Claude Code	CLI	Guide
Gemini CLI	CLI	Guide
OpenAI Codex CLI	CLI	Guide
OpenCode	CLI	Guide
Qwen Code	CLI	Guide

How to Achieve "One-Click Deploy" for AI Programming?

1. AI-Native

We're not just "glue code". Our built-in rule library is designed specifically for AI programming, enabling AI to directly generate "deployable" CloudBase best-practice code.

Prompt: Generate a user login feature
- AI automatically generates code following CloudBase standards
- Auto-configure database, cloud functions, security rules
- One-click deploy to cloud

2. One-Click Deploy

AI-automated MCP deployment flow, AI handles all cloud resource configuration from cloud functions, databases to static websites.

Prompt: Deploy current project to CloudBase
- Auto-detect project type (Web/Mini-program/Backend)
- Intelligent deployment parameter configuration
- Real-time deployment progress display
- Auto-return access link

3. Smart Debugging

Deployment error? Don't worry. AI automatically reads logs, analyzes issues, and generates fixes, truly achieving a develop-deploy-debug closed loop.

Prompt: There's an error: xxxx
- AI automatically views cloud function logs
- Analyze error causes
- Generate fix code
- Auto redeploy

4. Full-Stack Ready

Whether it's Web apps, mini-programs, or backend services, AI handles it all for you. You just focus on business logic.

Application Type	Tech Stack	Deployment Method
Web Apps	React/Vue/Next.js	Static Hosting + CDN
WeChat Mini-Programs	Native/UniApp	Mini-program Publishing
Backend Services	Node.js/Python	Cloud Functions/Cloud Run

5. Knowledge Search

Built-in intelligent vector search for CloudBase, WeChat Mini-Program and other professional knowledge bases, making AI understand CloudBase better.

Prompt: How to use cloud database to achieve real-time data synchronization?
- Intelligent search CloudBase knowledge base
- Return relevant documentation and best practices
- Provide code examples

6. Flexible Workflow

Support /spec and /no_spec commands, intelligently choose based on task complexity.

/spec - Complete workflow (Requirements → Design → Tasks → Implementation)
/no_spec - Fast iteration (Direct implementation)

Installation & Configuration

Prerequisites

• Node.js v18.15.0 or above
• Enabled Tencent CloudBase Environment
• Installed AI IDE that supports MCP (View supported IDEs)

Configuration Methods

Method 1: CloudBase AI CLI (Recommended)

# Install
npm install @cloudbase/cli@latest -g

# Use
tcb ai

Method 2: Manual MCP Configuration

Add MCP configuration according to your AI IDE:

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "cloudbase": {
      "command": "npx",
      "args": ["@cloudbase/cloudbase-mcp@latest"]
    }
  }
}

WindSurf

Add to .windsurf/settings.json:

{
  "mcpServers": {
    "cloudbase": {
      "command": "npx",
      "args": ["@cloudbase/cloudbase-mcp@latest"]
    }
  }
}

CodeBuddy

CodeBuddy has CloudBase MCP built-in, no configuration needed.

Other IDEs

View Complete configuration guide for other IDE configuration methods.

Use Cases

Case 1: Two-Player Online Gomoku

Development Process:

1. Input requirement: "Build a two-player online Gomoku website, support online battle"
2. AI generates: Web app + cloud database + real-time data push
3. Auto-deploy and get access link

Demo: Gomoku Game

View development screenshots

Development Process	Final Result

Case 2: AI Pet Mini-Program

Development Process:

1. Input: "Develop a pet-raising mini-program with AI-enhanced interaction"
2. AI generates: Mini-program + cloud database + AI cloud function
3. Import to WeChat DevTools to publish

View development screenshots and mini-program preview

Case 3: Smart Issue Diagnosis

When an app has issues, AI automatically views logs, analyzes errors, and generates fix code.

View smart diagnosis process

MCP Tools

39 tools covering environment management, database, cloud functions, static hosting, mini-program publishing, and other core features.

Category	Tools	Core Features
Environment	4	Login authentication, environment query, domain management
Database	11	Collection management, document CRUD, indexes, data models
Cloud Functions	9	Create, update, invoke, logs, triggers
Static Hosting	5	File upload, domain configuration, website deployment
Mini-Program	7	Upload, preview, build, configuration, debugging
Tool Support	3	Templates, knowledge base search, web search

View complete tool documentation | Tool specification JSON

More Resources

Documentation

• Quick Start
• IDE Configuration Guide
• Project Templates
• Development Guide
• Plugin System
• FAQ

Tutorials

Articles

• Develop a Neighborhood Item Recycling Mini-Program with CloudBase AI CLI
• Build and auto-deploy with OpenClaw + CloudBase
• Agent Skills in practice: don't let AI-built code die on localhost
• One-stop development of card flip game with CodeBuddy IDE + CloudBase
• Develop a WeChat mini-game in 1 hour
• More tutorials...

Videos

• CloudBase: Use AI to develop an Overcooked game
• Software 3.0: Best AI Programming Partner
• More videos...

Project Cases

• Gomoku Online Game
• Overcooked Co-op Game
• E-commerce Admin Panel
• More cases...

Community

WeChat Group

Scan to join WeChat tech exchange group

Other Communication Channels

Platform	Link	Description
Official Documentation	View Documentation	Complete CloudBase documentation
Issue Feedback	Submit Issue	Bug reports and feature requests

Project Activity

Contributors

Thanks to all the developers who have contributed to CloudBase MCP!

---

If this project is helpful to you, please give us a Star!

MIT © TencentCloudBase