ggsrun

High-performance Google Drive CLI and Model Context Protocol (MCP) Server for LLM/AI agents. Natively execute Google Apps Script (GAS) under a secure whiteliste

What is ggsrun?

High-performance Google Drive CLI and Model Context Protocol (MCP) Server for LLM/AI agents. Natively execute Google Apps Script (GAS) under a secure whitelisted runtime sandbox, automate transfers, and manage Drive infrastructure.

Overview of ggsrun

What it is

ggsrun is an enterprise-grade CLI application and Model Context Protocol (MCP) Server for Google Drive. It allows users to orchestrate Google Drive I/O operations and execute Google Apps Script (GAS) natively from a local terminal or via autonomous LLM/AI agents. Built on Go 1.26.4+, it uses a channel-based concurrent streaming architecture. It includes a native Security Sandbox to restrict Google Workspace APIs during autonomous executions.

Key features

  • Terminal GAS Development: Develop Google Apps Script using local text editors and terminals.
  • Dynamic Script Execution: Execute GAS by injecting values, arguments, and payloads dynamically.
  • Massively Parallel Downloads and Uploads: Concurrently pull and push files/folders from/to Google Drive with progress visualization.
  • Security Sandboxing: Integrates an embedded in-memory security sandbox wrapper (--sandbox) to guard Workspace resources.
  • MCP (Model Context Protocol) Integration: Running ggsrun mcp transforms the application into an autonomous JSON-RPC background server for LLM agents.
  • Flexible Authentication: Supports browser loopback OAuth2, Service Accounts, and direct Access Token injection.
  • Self-Healing Project Recovery: Restore remote GAS project to a clean initial state with ggsrun recover.

Use cases

  • Developing and testing Google Apps Script locally with a terminal-based workflow.
  • Automating large-scale file transfers and folder management across Google Drive, including Shared Drives.
  • Integrating Google Drive operations and GAS execution into AI agent pipelines via the MCP server.
  • Running script executions in a sandboxed environment to protect Workspace resources.

Getting started

Install via Go (requires Go 1.26.4+): bash $ go install github.com/tanaikech/ggsrun@latest Or download a pre-built binary from the official releases page for your OS/architecture. After installation, verify with: bash $ ggsrun --help Then follow the Setup & Onboarding Guide to configure GCP credentials and authorize the application.

License and pricing

The project is licensed under MIT and is open source (free).

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/tanaikechggsrun.svg)](https://yunodb.com/tools/tanaikechggsrun?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/tanaikechggsrun?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/tanaikechggsrun.svg" alt="Featured on YunoDB" height="20"></a>