Complete Gemini CLI Setup Guide for Your Terminal | HackerNoon

Gemini CLI has some handy built-in tools. You can use commands like:

Gemini CLI Tools Overview

• ReadFolder (ls). Lists files and folders in a directory—just like the shell ls command.
• ReadFile (read-file). Reads the full content of a single file, useful for summaries or analysis.
• ReadManyFiles (read-many-files). Reads multiple files at once, typically matching a glob pattern (e.g., all .js files)
• FindFiles (glob). Searches for files by pattern (e.g., find all config.json across your project).
• SearchText (grep). Searches within files for text, like finding all TODO comments.
• Edit (edit). Applies code changes via diffs. Gemini previews edits and asks for approval before applying them.
• WriteFile (write-file). Creates new files (for example, README.md) with user-provided content.
• Shell (shell). Runs commands you prefix with ! (e.g., !npm test) directly in the terminal .
• WebFetch (web-fetch). Fetches content from the web (HTML or JSON), enabling Gemini to analyze external data.
• GoogleSearch (web-search). Performs a Google search to ground responses with real-world information (e.g., explanation for an error).
• Save Memory (memoryTool). Stores facts or preferences during a session (like “I prefer async/await”) to improve consistency

To see all available tools, you can use the /tools command.

Advanced Features

You can add specific instructions for the AI for a particular project by creating a GEMINI.md file in your project’s root directory. Inside this file, you can define project rules, code styles, and the tools the agent should use. This ensures that the generated code is consistent with your project’s standards.

Google CLI MCP Integration

For most day-to-day uses, the built-in tools will suffice. But what if you want Gemini CLI to do something very domain-specific, like interact with specific APIs or use a specialized model (say an image generator or a security analysis tool)? This is where MCP (Model Context Protocol) comes in.

MCP is essentially an open standard that allows developers to add new tools/abilities to the AI by running a server that the CLI can communicate with. In Gemini CLI, you can configure “MCP servers” in a JSON settings file, and the CLI will treat those as additional tools it can use.

How to Set Up the MCP Server in Google CLI

As an example, I am going to show you how to set up the GitHub MCP server in Gemini CLI.

Inside your project folder, create a folder by using the command:

mkdir -p .gemini && touch .gemini/settings.json

Inside the file, add the following code:

{  
  "mcpServers": {  
    "github": {  
      "command": "npx",  
      "args": ["-y", "@modelcontextprotocol/server-github"],  
      "env": { "GITHUB_PERSONAL_ACCESS_TOKEN": "[YOUR-TOKEN]" }  
    }  
  }  
}

After that /quit , from the Gemini CLI, and then reopen it.

Write /mcp command, and you will see a list of GitHub tools.

Now you, Agent, can interact with GitHub. That simple! 🙂

Gemini CLI Pricing

You can try it free for personal usage, but there is also a paid version that is billed based on token usage.

Free Preview Tier

• Cost: Free with Google account
• Limits: Up to 60 requests/min and 1,000 requests/day
• Great for individual developers and small-scale use

Paid / API Key Usage

• Use your own Gemini API key for higher usage
• Billed based on tokens consumed (model and usage dependent)

Enterprise Options

• Available through Gemini Code Assist Standard or Enterprise plans
• Includes advanced features like governance, audit logs, and shared quotas

Conclusion

As you can see, Gemini CLI is a really powerful tool with a lot of potential. I’m excited to see how I’ll be using it in my daily workflow.

If you write code, debug things, or manage files often, this tool is worth checking out.

If you have any feedback, please share it in the comments below. 😉

Cheers!