tanaike - Google Apps Script, Gemini API, and Developer Tips

The Thinker

Enhanced Guide to Using Prompts in Gemini CLI

Gists

Abstract

This report provides a comprehensive overview of how to utilize prompts within the Gemini Command-Line Interface (CLI). Leveraging a Google Apps Script MCP server, we will explore practical examples, including roadmap generation, real-time weather inquiries, and Google Drive file searches. This enhanced document offers more in-depth explanations and a broader context to empower users in their understanding and application of these powerful features.

Introduction

The Model Context Protocol (MCP) establishes a standardized framework for servers to offer clients predefined, structured prompt templates. These user-controllable prompts, customizable with arguments, are engineered to streamline interactions with large language models. The Gemini CLI, starting with version v0.1.15, integrates support for these prompts, significantly expanding its capabilities.

Updated: GAS Library - ToolsForMCPServer

ToolsForMCPServer was updated to v1.0.12

  • v1.0.12 (July 31, 2025)

    1. At Gemini CLI v0.1.15, prompts/list was called even when prompts wasn’t included in capabilities. This resulted in the error Error discovering prompts from gas_web_apps: MCP error -32001: Request timed out when prompts wasn’t returned for prompts/list. To resolve this, I updated ToolsForMCPServer to return an empty array for prompts, which eliminated the error. Consequently, with this update in v1.0.12, you can now set custom prompts and resources.

You can see the detailed information here https://github.com/tanaikech/ToolsForMCPServer

Next-Level Data Automation: Gemini CLI, Google Calendar, and MCP

Gists

Abstract

This report demonstrates managing Google Calendar from the command line using Gemini CLI and an MCP server, enabling powerful, scriptable automation for your schedule.

Introduction

Following up on my previous report, “Next-Level Data Automation: Gemini CLI, Google Sheets, and MCP,” I’m excited to present the next installment in this series. My earlier report, published on Medium, detailed an innovative approach to managing Google Sheets through the powerful combination of Gemini CLI and an MCP server. Ref

Updated: GAS Library - ToolsForMCPServer

ToolsForMCPServer was updated to v1.0.10

  • v1.0.10 (July 26, 2025)

    1. When I updated Gemini CLI from v0.1.12 to v0.1.13, an issue related to the schema of MCP occurred. Ref So, as a workaround at the time, I updated this library. But when I updated Gemini CLI to v0.1.14, I confirmed that the previous schema could be used. So, I reimplemented the previous schema. By this, the request body for APIs can be directly generated using Gemini CLI v0.1.14.

You can see the detailed information here https://github.com/tanaikech/ToolsForMCPServer

Updated: GAS Library - ToolsForMCPServer

ToolsForMCPServer was updated to v1.0.8

  • v1.0.8 (July 23, 2025)

    1. An issue occurred when I updated Gemini CLI from v0.1.12 to v0.1.13. Ref Fortunately, Google is already aware of this issue, and I’m awaiting a resolution. In the meantime, I’ve received emails about it, so I’ve updated ToolsForMCPServer for Gemini CLI v0.1.13. The detailed updates are as follows: I confirmed that all tools in ToolsForMCPServer v1.0.8 worked when tested with Gemini CLI v0.1.13.
    • oneOf has been removed from the schema of each tool.
    • Following this report, the request body is now generated on the MCP server side. Therefore, when using the tools manage_google_docs_using_docs_api, manage_google_sheets_using_sheets_api, and manage_google_slides_using_slides_api, please use your API key for the Gemini API.

You can see the detailed information here https://github.com/tanaikech/ToolsForMCPServer

Generating Request Body for APIs using Gemini

Gists

Abstract

Effortlessly generate API request bodies from natural language commands. This guide demonstrates using Gemini and Google Apps Script to streamline automation and accelerate development for Google Workspace APIs and beyond.

Introduction

In a recent article, “Managing Google Docs, Sheets, and Slides by Natural Language with Gemini CLI and MCP,” I showcased a powerful method for dynamically creating API request bodies using natural language. This approach, utilizing the Gemini CLI and a My Custom Proxy (MCP) server, allows users to manage Google Workspace applications with simple, human-readable commands. The core concept is that generating API request bodies directly from natural language within a script can dramatically streamline automation and development.