Skip to main content

CloudBase AI Toolkit + Gemini CLI

🚀 Gemini CLI + CloudBase = Full-stack application from idea to launch in minutes.

GitHub Stars Open Source License

💡 Why choose Gemini CLI + CloudBase AI Toolkit?
Gemini CLI is an open-source command-line AI agent launched by Google, providing powerful local AI workflows and MCP protocol support, with a 1M token context window and rich built-in tools. Combined with CloudBase AI Toolkit, it allows you to describe requirements in natural language, and AI automatically generates and deploys full-stack applications to the Tencent Cloud development platform. It is especially suitable for command-line enthusiasts, automated script development, and rapid prototyping.

✨ Core Advantages​

🎯 Development Efficiency⚡ Deployment Speed🛡️ Stability and Reliability
AI automatically generates code and architecture
Built-in best practice rules for cloud development
Intelligent error fixing and optimization		One-click deployment to Tencent Cloud development
Domestic CDN accelerated access
Serverless architecture with no Ops required		Platform verified by 3.3 million developers
Enterprise-grade security and stability
Comprehensive monitoring and logging system

🚀 5-Minute Quick Start​

Select pre-configured project templates, ready to use out-of-the-box:

Method 2: Integrate with existing projects​

If you already have a project, you can integrate in just 3 steps:

# 1. Configure MCP (See detailed steps below for specific configuration)
# 2. Download AI Rules
# 3. Start Using

After configuration is complete, tell the AI: "Log in to CloudBase" to begin!

🔧 Detailed Configuration Guide​

Step 1: Install Gemini CLI​

Ensure Node.js 18+ is installed, then install Gemini CLI globally:

npm install -g @google/gemini-cli

Or run directly:

npx @google/gemini-cli

On first run, log in with a personal Google account to get free quota (60 requests per minute, 1000 requests per day).

Step 2: Configure CloudBase MCP​

[!TIP] If the number of tools remains 0 after installation, please refer to the FAQ

If using a template project, the MCP configuration is pre-configured.

If not starting from a template, create the .gemini/settings.json file in the user home directory (~) or project directory:

{
  "mcpServers": {
    "cloudbase": {
      "command": "npx",
      "args": ["npm-global-exec@latest", "@cloudbase/cloudbase-mcp@latest"],
      "env": {
        "INTEGRATION_IDE": "Gemini"
      }
    }
  }
}

One-click Configuration Verification:

Run Gemini CLI, then use the following commands:

gemini
> /mcp

View the configured MCP servers. If CloudBase MCP has not been configured yet, you can manually add the configuration file.

Step 3: Enable AI Rules​

The template project's root directory already includes the GEMINI.md file containing CloudBase development rules.

If it is an existing project, say to the AI in Gemini CLI:

Download CloudBase AI rules in the current project

If you only want to download Gemini CLI-related configuration files to avoid cluttering your project files, you can specify the IDE type:

Download CloudBase AI rules in the current project, containing only Gemini CLI configuration

Step 4: Start Development​

Start Gemini CLI:

gemini

Then tell the AI:

Log in to CloudBase

🎯 Get Started​

After configuration is complete, tell the AI:

Log in to CloudBase

Then you can start development, for example:

Create an online voting system that supports creating polls, participating in voting, and result statistics, using cloud database for storage, and finally deploy it.

💡 Gemini CLI Key Features​

🔧 Built-in Tools​

Gemini CLI provides a rich set of built-in tools:

  • Google Search: Real-time information search
  • File Operations: Read, write, and edit files
  • Shell Commands: Execute system commands
  • MCP Support: Extend third-party capabilities

View all available tools:

> /tools

📚 Context Memory​

Gemini CLI supports hierarchical GEMINI.md files:

  • Global rules: ~/.gemini/GEMINI.md
  • Project rules: project root directory/GEMINI.md
  • Component rules: GEMINI.md in subdirectories

View currently loaded rules:

> /memory show

Refresh rules:

> /memory refresh

⚡ Command Mode​

Common commands:

  • /tools - View available tools
  • /mcp - View MCP server status
  • /memory - Manage context memory
  • /stats - View session statistics
  • !command - Execute Shell commands

🚀 YOLO Mode​

Automatically execute all operations without confirmation:

gemini --yolo

⚠️ Warning: YOLO Mode will automatically execute all operations. Use with caution.

🌟 CloudBase AI Toolkit Open-Source Project​

🔥 Join the Open-Source Community​

GitHub CNB Community

⭐ Star the Project | 🤝 Contribute Code | 💬 Technical Discussion

🛠️ Troubleshooting​

Frequently Asked Questions​

Q: Gemini CLI connection failed? A:

  1. Check the network connection
  2. Confirm Google account login status
  3. Check the configuration format of .gemini/settings.json

Q: MCP server failed to start? A:

  1. Confirm Node.js version >= 18
  2. Check the MCP configuration format
  3. Run the /mcp command to view status

Q: Does the AI-generated code not meet expectations? A:

  1. Check if the GEMINI.md file exists
  2. Use /memory show to view current rules
  3. Provide more detailed requirement descriptions

For more questions, refer to: Complete FAQ

🔗 Official Resources​

📚 Related Resources​

💬 Technical Discussions​

WeChat Technical Exchange Group​

WeChat group QR code
Scan the QR code to join the WeChat technical exchange group

🚀 Get started with Gemini CLI + CloudBase AI Toolkit immediately

Get Started | View Templates | GitHub Repository