What are the prerequisites to use this server?
Node.js 16 or higher, a Google Cloud Platform project with the Google Sheets API enabled, and OAuth 2.0 credentials (client ID, client secret, refresh token).
@mattcoatsworth
基本情報
概要はまだありません
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。
A comprehensive Model Context Protocol (MCP) server for interacting with the Google Sheets API. It provides tools and resources for managing spreadsheets, sheets, values, and developer metadata, intended for developers building AI or automation workflows that need to read and write Google Sheets data.
Clone the repository, install dependencies with npm install, and create a .env file with your Google OAuth 2.0 credentials (CLIENT_ID, CLIENT_SECRET, REDIRECT_URI, REFRESH_TOKEN). Run the server with npm start, or use npm run dev for development mode and npm run inspect to test with the MCP Inspector.
Node.js 16 or higher, a Google Cloud Platform project with the Google Sheets API enabled, and OAuth 2.0 credentials (client ID, client secret, refresh token).
The server uses OAuth 2.0. You must provide a CLIENT_ID, CLIENT_SECRET, REDIRECT_URI, and a REFRESH_TOKEN in the `.env` file.
Tools for spreadsheet management (create, get, batch update), sheet management (copy, add, delete, update properties), values management (get, update, append, clear, batch get/update), and developer metadata (get, create, update, delete).
Resources follow the pattern `sheets://spreadsheet/{spreadsheetId}`, `sheets://spreadsheet/{spreadsheetId}/sheet/{sheetName}`, `sheets://spreadsheet/{spreadsheetId}/values/{range}`, and `sheets://spreadsheet/{spreadsheetId}/metadata`.
MIT.

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.


Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott
コメント