MCPApp

Name: MCPApp
Author: tanaikech

@tanaikech

About MCPApp

This text introduces the Model Context Protocol (MCP) for AI interaction, exploring Google Apps Script (GAS) as a server option. It shows feasibility with a sample but notes the lack of a GAS SDK, aiming to encourage understanding and development.

#mcp #google-apps-script #model-context-protocol

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "gas_web_apps": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://script.google.com/macros/s/###/exec?accessKey=sample"
      ],
      "env": {}
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCPApp?

MCPApp is a Google Apps Script library that implements a Model Context Protocol (MCP) server, allowing AI applications to securely access and leverage data from Google Workspace services (Drive, Calendar, Sheets, etc.) through a standardized protocol.

How to use MCPApp?

Create a standalone or container-bound Google Apps Script project, install the MCPApp library using its project key (1TlX_L9COAriBlAYvrMLiRFQ5WVf1n0jChB6zHamq2TNwuSbVlI5sBUzh), then write a doPost function that calls new MCPApp.mcpApp({ accessKey: "sample" }).server(object) with a custom server response and function definitions. The sample shows how to implement tools, resources, and prompts.

Key features of MCPApp

Provides a GAS library to deploy MCP servers easily.
Supports MCP tools, resources, and prompts.
Enables AI to access Google Drive and Google Calendar data.
Includes sample functions for file search and calendar schedule retrieval.
Uses JSON-RPC 2.0 for client-server communication.

Use cases of MCPApp

Build an MCP server that queries Google Drive files and returns metadata to an AI assistant.
Let an AI retrieve today’s schedule from Google Calendar via a MCP resource.
Create custom prompts that combine Google Workspace data for AI‑powered workflows.
Enable internal AI tools to interact with Google Workspace without exposing raw APIs.
Serve as a reference implementation for developing a dedicated GAS MCP SDK.

FAQ from MCPApp

How do I install the MCPApp library?

Add the library to your Google Apps Script project using the project key 1TlX_L9COAriBlAYvrMLiRFQ5WVf1n0jChB6zHamq2TNwuSbVlI5sBUzh. You can also copy and paste the library script directly.

What MCP features are implemented in the sample?

The sample implements tools/list, tools/call, resources/list, resources/read, prompts/list, and prompts/get capabilities.

Can I use MCPApp with container‑bound GAS projects?

Yes, both standalone and container‑bound script types are supported.

What runtime or dependencies are required?

MCPApp runs within Google Apps Script; no additional runtime or external dependencies are needed beyond the standard GAS services.

How are transport and authentication handled?

The server is exposed via a Google Web App (deployed as doPost). Authentication is handled by an accessKey passed to the mcpApp constructor; the sample uses "sample".

Comments

More Other MCP servers

Inbox Zero AI MCP

elie222

The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.

11.6K

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K