Updated: GAS Library - MCPApp

MCPApp was updated to v2.0.7

  • v2.0.7 (August 6, 2025)

    1. Starting with v2.0.7, you can now selectively enable or disable the LockService.

      • By default, this library runs with the LockService enabled. To disable it, simply modify return new MCPApp.mcpApp({ accessKey: "sample" }) to return new MCPApp.mcpApp({ accessKey: "sample", lock: false }).
      • When the LockService is disabled (lock: false), asynchronous requests from clients like the Gemini CLI may see an increase in processing speed. However, it’s important to note that the maximum number of concurrent requests must not exceed 30. Please use this option with caution.

You can see the detail information here https://github.com/tanaikech/MCPApp

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

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

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

Google OAuth Verification & Application Privacy Policy

Registered Application Name: Workspace & Gemini AI Orchestration Engine

Application Purpose & Core Functionality:

This web page serves as the official homepage and privacy compliance interface for the application "Workspace & Gemini AI Orchestration Engine". This specialized developer utility is designed to research, benchmark, and optimize advanced integrations between Google Workspace services, the Google Apps Script API, and Gemini AI models (via Google Vertex AI / Gemini API endpoints).

The application facilitates automated multi-agent scaffolding, programmatic script deployment, project resource management, and structural analysis of Google Apps Script projects. It allows developers and autonomous AI agents (operating via Model Context Protocol / MCP) to securely evaluate execution performance, implement high-performance batch requests, and test agent-to-agent (A2A) workflows within a controlled and structured environment.

Google User Data Policy Compliance Statements:

1. Data Access & Specific Usage

Our application explicitly requests access to specific Google user accounts through OAuth scopes required strictly for interacting with the Google Apps Script API and Google Workspace endpoints. This access is utilized solely to execute user-initiated or agent-orchestrated programmatic operations—such as creating, modifying, deploying, or benchmarking script projects and executing automated workflows. No background automated extraction occurs without explicit session initiation.

2. Data Storage & Zero-Retention Policy

Adhering to a strict Zero-Retention Model, this application does not store, log, or persist any personal data, OAuth tokens, script source codes, or Google account configurations on any external server, database, or persistent storage medium. All data processing and API responses are handled entirely in-memory or securely on the client side within the active session context, ensuring complete cryptographic transient isolation.

3. Data Sharing & Third-Party Non-Disclosure

We maintain absolute data privacy. No data accessed via Google OAuth scopes is shared, sold, rented, or transferred to third-party entities, advertising networks, or data brokers. All data transmissions are strictly point-to-point, encrypted in transit using industry-standard protocols, and limited entirely to the direct channel between the execution environment and Google's official API gateways.

For inquiries regarding this developer application, technical benchmarks, or verification compliance, please refer to the official documentation and repositories linked on this homepage (tanaikech.github.io).