CloudBase AI Toolkit + OpenAI Codex CLI
💡 Why choose OpenAI Codex CLI + CloudBase AI Toolkit? OpenAI Codex CLI is a command-line tool based on the OpenAI Codex model, supporting the MCP (Model Context Protocol) protocol, with powerful code generation and comprehension capabilities. Combined with the 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 developers and scenarios requiring efficient AI-assisted development.
✨ Core Advantages
🎯 Development Efficiency | ⚡ Deployment Speed | 🛡️ Stability and Reliability |
---|---|---|
AI automatically generates code and architecture Built-in best practices for cloud development Efficient command-line interaction | 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
Method 1: Use project templates (Recommended)
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. Install OpenAI Codex CLI
# 2. Configure MCP (See detailed steps below for specific configuration)
# 3. Start Codex CLI and begin using it
After configuration is complete, tell the AI: "Log in to CloudBase" to begin!
🔧 Detailed Configuration Guide
Step 1: Install OpenAI Codex CLI
npm install -g @openai/codex
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, there are two configuration methods:
Method 1: Use project configuration file (Recommended)
Create the .codex/config.toml
file in the project root directory:
[mcp_servers.cloudbase]
command = "npx"
args = ["npm-global-exec@latest", "@cloudbase/cloudbase-mcp@latest"]
env = { INTEGRATION_IDE = "CodeX" }
Then specify the configuration file when starting:
codex --config .codex/config.toml
Method 2: Global Configuration
Create the ~/.codex/config.toml
file in the user's home directory:
[mcp_servers.cloudbase]
command = "npx"
args = ["@cloudbase/cloudbase-mcp@latest"]
Step 3: Enable AI Rules
The template includes the AGENTS.md
file, and OpenAI Codex CLI will automatically recognize Cloud Development best practices. If not starting from a template, you can have the AI download the Cloud Development rules:
Download CloudBase AI rules in the current project
If you only want to download configuration files related to OpenAI Codex CLI to avoid cluttering your project files, you can specify the IDE type:
Download CloudBase AI rules in the current project, containing only the OpenAI Codex CLI configuration
Step 4: Start Development
Start OpenAI Codex CLI:
codex
If using the project configuration file:
codex --config .codex/config.toml
Converse with the AI in Codex CLI:
Log in to CloudBase
🎯 Common Commands
After the configuration is complete, 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.
OpenAI Codex CLI has powerful code comprehension capabilities, enabling deep analysis of project structures and generation of high-quality code.
🌟 CloudBase AI Toolkit Open-Source Project
🛠️ Troubleshooting
Frequently Asked Questions
Q: MCP connection failed? A:
- Check if the file format of
.codex/config.toml
is correct - Verify the availability of the npx command:
npx --version
- Restart the Codex CLI application
- Check the network connection status
Q: Project rules not taking effect? A:
- Confirm that the
AGENTS.md
file is in the project root directory - Check if the file content format is correct
- Restart Codex CLI
Q: Does the AI-generated code not meet expectations? A:
- Describe the functional requirements and technical specifications in detail
- Use project templates to ensure specification consistency
- Implement complex projects step by step in modules
Q: How to use the project configuration file? A:
- Create the
.codex/config.toml
file in the project root directory - Use
codex --config .codex/config.toml
at startup - This allows different projects to use different configurations
For more questions, refer to: Complete FAQ
📚 Related Resources
- 📖 Developer Guide - Learn more about development best practices
- 🎯 Use Cases - View practical application examples
- 🔧 MCP Tools - Learn about all available tools
- ❓ FAQ - View frequently asked questions
- OpenAI Codex CLI Official Documentation - OpenAI Codex CLI official documentation
💬 Technical Discussions
WeChat Technical Exchange Group

Scan the QR code to join the WeChat technical exchange group
🚀 Get started with OpenAI Codex CLI + CloudBase AI Toolkit immediately