What runtime and dependencies does it require?
Python (with virtual environment) and the packages in `requirements.txt`. The Google Sheets, Drive, Docs, and Slides APIs must be enabled in the Google Cloud Console.
@dev-ithitchhiker
基本情報
A lightweight MCP Server for integrating Google Docs, Sheets, and Slides with custom applications. Enables seamless document management, real-time collaboration, and API-based automation.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"mcp-google-docs": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
MCP Google Workspace Integration is an MCP (Metoro Control Protocol) tool that provides programmatic access to Google Workspace services including Google Docs, Sheets, Slides, and Drive. It is designed for developers who need to automate document creation, spreadsheet manipulation, presentation management, and file operations within Google Workspace.
Set up a Python virtual environment, install dependencies from requirements.txt, enable the required Google APIs (Sheets, Drive, Docs, Slides), create an OAuth 2.0 client secret in Google Cloud Console, and set the MCPGD_CLIENT_SECRET_PATH and MCPGD_FOLDER_ID environment variables. Then run python main.py and use the provided MCP commands such as mcp list_files, mcp get_sheet_data, mcp create_document, or mcp create_presentation.
Python (with virtual environment) and the packages in `requirements.txt`. The Google Sheets, Drive, Docs, and Slides APIs must be enabled in the Google Cloud Console.
OAuth 2.0 – you must create a client secret in Google Cloud Console and point the `MCPGD_CLIENT_SECRET_PATH` environment variable to the JSON file. A token file is stored locally (default path `~/.mcp_google_spreadsheet.json`) for subsequent use.
All data remains in your Google Workspace account. The only local data is the OAuth token file used to store authorization credentials.
The README does not mention any specific limits. Google API quotas and your Workspace plan apply.
The README does not specify the transport; it relies on the MCP (Metoro Control Protocol) standard. All communication goes through Google’s API endpoints over HTTPS.

The Cloud is the AI-native workspace that gives every AI — Claude, ChatGPT, Gemini, and other Frontier & Free or Local models — shared memory and real agents. Not cloud computing: thecloud.so is one workspace where your
Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.
Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.

Exact, shared memory for AI agents: a hierarchical database where totals always add up, every write is attributed to the agent and person behind it, and any figure traces back to its source file. Agents create databases,
コメント