Connect to CloudBase MCP

After connecting via the Model Context Protocol (MCP), you can operate CloudBase services directly in your AI chat—no need to switch between your IDE and the console.

CloudBase MCP supports Local Mode (run via npx on your machine) and Hosted Mode (connect to the cloud over HTTP). In Local Mode you can configure environment variables; in Hosted Mode you can control plugins via a URL.

See Connection Modes: Local vs Hosted.

Prerequisites

Before you start, make sure you have:

Node.js and a CloudBase environment ready

Node.js: Install Node.js v18.15.0 or later:

node --version

If you don’t have it installed, download it from the Node.js website.

CloudBase environment: Follow the doc Create a CloudBase environment. New users can start for free.

Connect Your AI Tool

Pick your AI development tool and follow the setup guide:

Client

Configure your AI tool to connect with CloudBase capabilities. Supports local and hosted connection. See connection modes.

Step 1: Install / Configure CloudBase

Use project template (recommended) - Template includes MCP configuration and AI rulesView templates

Install in one click:

Add to Cursor

Or manual configuration:

Or add this configuration to .cursor/mcp.json:

json

1{
2  "mcpServers": {
3    "cloudbase": {
4      "command": "npx",
5      "args": ["@cloudbase/cloudbase-mcp@latest"],
6      "env": {
7        "INTEGRATION_IDE": "Cursor"
8      }
9    }
10  }
11}

Need help?View Cursor docs

Step 2: Chat with AI

Enter the following in your AI chat in order:

prompt

Install CloudBase Skills: run npx skills add tencentcloudbase/cloudbase-skills -y

Use CloudBase Skills: 实现小程序与 CloudBase 的完整集成

Manually Confirm Tool Calls

Most MCP clients (e.g. Cursor) will ask you to manually confirm every tool call. We recommend keeping this enabled and carefully reviewing the tool call details before execution.

Start Using It

After setup, type in your AI chat:

Log in to CloudBase

Your AI will guide you through login and environment selection. Then you can start describing requirements in natural language and let the AI build your app.

Examples

End-to-end example:

Create a todo app and deploy it

The AI can automatically: generate code, create databases, deploy cloud functions, configure static hosting, and return an access link.

Step-by-step examples:

• "Create a users table" - AI creates database collections/tables
• "Deploy this function" - AI uploads and configures cloud functions
• "Deploy the frontend to CDN" - AI uploads files and configures hosting

Detailed requirement example:

Create a todo app with:
- Add / delete / edit todos
- Store data in the cloud database
- Support marking items as completed
- Deploy to the cloud

AI Skill Scenarios

身份认证

身份认证：配置管理

配置管理认证提供商

身份认证：Web SDK

Web SDK 身份认证

身份认证：微信小程序

微信小程序身份认证

身份认证：App 集成

Android、iOS 原生应用

身份认证：Node.js 服务端

Node.js 服务端身份认证

数据库

文档数据库：Web SDK

Web SDK 文档数据库

文档数据库：小程序 SDK

小程序 SDK 文档数据库

关系型数据库：工具与规则

MySQL 关系型数据库

关系型数据库：Web SDK

Web SDK 关系型数据库

数据库：数据模型创建

复杂数据模型设计

数据库：App 集成

Android、iOS 原生应用

后端开发

后端开发：云函数

Node.js 云函数

后端开发：云托管

Node.js、Python、Go、Java 等

应用集成

应用集成：Web 应用

React、Vue、Vite、浏览器验证

应用集成：微信小程序

小程序开发与集成

应用集成：UI 设计

专业界面设计指南

应用集成：App 集成

Android、iOS 原生应用

AI

在 Web 应用中集成 AI 功能

在 Web 应用中调用 AI

在 Node.js 后端中集成 AI 功能

在后端服务中调用 AI

在微信小程序中集成 AI 功能

在小程序中调用 AI

开发工具

开发工具：Spec 工作流

需求分析、技术设计、任务拆分

开发工具：CloudBase 平台

平台知识库和最佳实践

Video Tutorials

Want to learn CloudBase MCP via videos? See tutorials and practical cases.