gemini-cli-extensions/workspace

Access Google Workspace when using Gemini CLI

What it solves

It allows users to manage Google Workspace apps—including Docs, Sheets, Slides, Gmail, Chat, and Calendar—directly from the command line via the Gemini CLI, removing the need to switch between the terminal and a web browser.

How it works

The project is an extension for the Gemini CLI that provides a set of tools and commands (such as /calendar:get-schedule and /drive:search) to interact with Google Workspace APIs. It supports both local and headless/remote environments (like SSH or WSL) through a specialized authentication process.

Who it’s for

Developers and power users who prefer working in a terminal environment and want to integrate their Google Workspace productivity tools into their AI-driven command-line workflow.

Highlights

  • Integrated management of Google Docs, Sheets, Presentations, and Calendar events.
  • Support for headless authentication for remote environments like Cloud Shell or SSH.
  • Ability to create documents and search Google Drive using natural language prompts.
  • Built as an MCP server to grant the AI agent ability to read, modify, and delete account data.

Related

  • Project
    google-gemini/gemini-cli

    An open-source AI agent for the terminal that provides direct access to Gemini models for code analysis, automation, and system integration.

  • Project
    googleworkspace/cli

    A unified CLI for all Google Workspace APIs that dynamically generates its command surface, providing structured JSON output for both humans and AI agents.

  • Project
    bwendell/gemini-desktop

    A privacy-first desktop client for Google Gemini that adds native controls, global hotkeys, and zero telemetry to the AI experience.

  • Project
    a-bonus/google-docs-mcp

    A Node.js MCP server that lets AI agents (Claude Desktop, Cursor, etc.) read, edit, and manage Google Docs, Sheets, Drive files, Gmail messages, Calendar events, and Apps Script projects via natural‑language‑style tool calls. It works locally via `npx` after OAuth setup or can be deployed to Cloud Run for team‑wide use.

  • Project
    jacob-bd/gemini-notebook-mcp-cli

    A Python package that provides a `nlm` CLI and a local MCP server to programmatically manage Google Gemini Notebook (list/create notebooks, add sources, generate audio/video, etc.) and expose those actions to AI agents (Claude, Cursor, Gemini‑CLI, etc.). Install via `uv`/`pip`, log in with Google cookies (optionally encrypted), run `nlm setup` to connect your AI tools, then use simple commands or natural‑language prompts via the MCP server.