Abstract

Gemini Spark, Google's 24/7 autonomous AI agent, seamlessly connects with Google Workspace. However, connecting to arbitrary external APIs requires extended integration. This article demonstrates how integrating Google Apps Script (GAS) as a Model Context Protocol (MCP) server or Webhook endpoint expands Gemini Spark's capabilities, enabling enterprise-grade workflow automation.

Introduction

Gemini Spark was officially announced at Google I/O 2026 on May 19, 2026, and its service in Japan began on July 16, 2026. Ref Gemini Spark is Google's first always-on AI agent that runs continuously in the cloud 24/7, even when your PC is closed, to complete tasks on your behalf. Unlike traditional Q&A-style chat AIs, it can autonomously execute complex workflows across multiple Google applications. Its core functionalities are built around three main pillars: Tasks, Skills, and Schedules.

Gemini Spark features built-in integrations for managing Google Workspace applications. By combining these built-in applications, Gemini Spark can process various user tasks. Furthermore, Google Apps Script (GAS) extends control beyond Google Workspace to manage a vast array of Google APIs and external services. Recently, Google Apps Script achieved General Availability (GA) as a core service in Google Workspace, providing enterprise-grade data protection, robust administrative controls, and standard technical support. Ref