Skip to main content

Gemini CLI + CloudBase AI Toolkit (MCP): A Step-by-Step Guide

CloudBase TeamCloudBase Team
One min read

Follow this guide to inject the power of Tencent CloudBase into Gemini CLI. Once set up, you can use Gemini CLI to work with CloudBase's development, deployment, and operations resources.

Step 1: Install and prepare Gemini CLI

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

npm install -g @google/gemini-cli

Step 2: Install the CloudBase AI Toolkit

gemini extensions install https://github.com/TencentCloudBase/CloudBase-AI-ToolKit

Next, tell the AI: "Log in to CloudBase."

Pick one of the options Gemini CLI offers (1, 2 or 3) and press Enter to continue. A CloudBase console page will open in your browser — confirm the authorization and select your environment there.

Step 3: Use the CloudBase extension (example prompt)

You can say to the AI:

"Build an online polling system that supports creating polls, voting, and result statistics. Use a cloud database for storage, and deploy it when done."

That completes the full loop — using Gemini CLI to call the CloudBase AI Toolkit MCP to develop and deploy an application.

References

Build your next app on CloudBase

An all-in-one backend covering database, cloud functions, static hosting, and AI capabilities.