What tools does MCP Google Sheets Server provide?
It provides three tools: `list_sheets(spreadsheet_id)`, `read_cells(spreadsheet_id, range_name)`, and `write_cells(spreadsheet_id, range_name, values)`.
@shionhonda
基本情報
Model Context Protocol (MCP) server that allows interaction with Google Sheets
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-gsheet": {
"command": "uv",
"args": [
"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 Sheets Server is a Model Context Protocol (MCP) server that enables interaction with Google Sheets. It is intended for AI agents or tools that need to list sheets, read cell ranges, and write data to spreadsheets, but it does not manage Google Drive files.
Set the GOOGLE_APPLICATION_CREDENTIALS environment variable to the absolute path of your service account JSON key, clone the repository, create a Python 3.11+ virtual environment with uv, install dependencies, then run mcp dev server.py (development) or mcp run server.py (production). The server communicates over standard input/output (stdio).
It provides three tools: `list_sheets(spreadsheet_id)`, `read_cells(spreadsheet_id, range_name)`, and `write_cells(spreadsheet_id, range_name, values)`.
No. The server explicitly does **not** provide tools for managing Google Drive files. Access is restricted to spreadsheet content only.
Python 3.11+, a Google Cloud Project with the Google Sheets API enabled, and a downloaded service account key file (JSON). Dependencies are managed via `uv`.
Set the environment variable `GOOGLE_APPLICATION_CREDENTIALS` to the absolute path of your service account JSON key file. The service account must have the "Editor" role on the target Google Sheets.
Use `mcp dev server.py` for development with MCP Inspector, or `mcp run server.py` for production. For Claude Desktop, add a JSON configuration block pointing to `uv` and the server path.

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

Model Context Protocol Servers

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
Painless E2E Automation for Mobile and Web
🚀 The fast, Pythonic way to build MCP servers and clients.
コメント