← Discover MCPs and Agents
g
MCPAI & MLGitHub

gemini-llm-cli

Use FREE AI gemini large languange model in command line to create command line and coding assistant without ever leaving your terminal

Links

Repository

README

From the repo.

GEMINI on your Terminal

Overview

GEMINI in command-line and coding assistant designed to keep you productive without ever leaving your terminal. With GEMINI, you can quickly find answers to technical questions or engage in interactive sessions to solve complex problems right from the command line.

Installation

Follow these steps to set up GEMINI:

npm i -g gemini-llm-cli

  1. Create a GEMINI API Key

  2. Run GEMINI

    • Start the program by typing the following command in your terminal: 
      chat

  3. Configure Your API Key

    • On your first run, GEMINI will prompt you to enter your API key. Simply paste the key into the prompt, and you’re ready to go!

Usage

Quick Answers

Get instant help with specific topics or commands by providing your query directly in the terminal:

chat tailwindcss border radius

Interactive Chat Sessions

Engage in a full conversation or problem-solving session by launching GEMINI without any additional arguments:

chat

Gain Superpowers with pipe

Find docs, create question to have knowledge-based AI assistant

(<docs-source> & <question>) | chat

Example:

(pip --help & echo How can I see package size?) | chat

Tunning and custom system prompt

Open node_modules source file (use which chat to easier find) and open the main .env file, change the SYSTEM variable to your desired system prompt.

SYSTEM="You are helpfull command line assistant"

Features

  • Chat Session: Remember context and previous chat history
  • Seamless Integration: Access GEMINI directly from your terminal for maximum productivity.
  • Quick Queries: Instantly retrieve answers without disrupting your workflow.
  • Interactive Sessions: Solve complex problems or ask detailed questions in a chat format.
  • Easy Setup: Configure once, use effortlessly every time.

Collected info

  • ★ 2 stars
  • Language: JavaScript
  • Source updated: 11/15/2025

Config for your environment

Replace {MCP_ENDPOINT_URL} with this MCP’s endpoint URL (from its repo or docs above). No API key — you connect directly.

Tool

OS

Config file: ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp-server": {
      "url": "{MCP_ENDPOINT_URL}"
    }
  }
}

Paste into mcpServers in the config file. Restart Cursor after saving.

If this MCP is also published on mcpchannel.ai, you can subscribe from Browse and use the gateway config there instead.