What runtime dependencies does Spreadsheet MCP Server require?
Node.js and npm are required. The project uses TypeScript and compiles to JavaScript.
@HosakaKeigo
Basic information
No overview available yet
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"spreadsheet-mcp-server": {
"command": "npx",
"args": [
"@modelcontextprotocol/inspector",
"node",
"build/index.js"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
It is a Model Context Protocol (MCP) server that provides access to Google Spreadsheet data, enabling LLMs to directly use spreadsheet information.
Clone the repository, install dependencies with npm install, configure environment variables (GAS_WEB_APP_URL and GAS_API_KEY) in a .env file, then build with npm run build. Start the server standalone with npm start or integrate it with Claude for Desktop by editing claude_desktop_config.json. If environment variables are not set, the server runs in mock mode.
Node.js and npm are required. The project uses TypeScript and compiles to JavaScript.
Set the environment variables `GAS_WEB_APP_URL` (the URL of your Google Apps Script Web App) and `GAS_API_KEY` (the API key for accessing that Web App). If not set, the server runs in mock mode.
Data remains in the user's Google Sheets. The server accesses it via a Google Apps Script Web App, without storing spreadsheets locally.
The server uses MCP over stdio by default. No other transports are mentioned. Authentication is handled via an API key passed to the GAS Web App; no alternative auth methods are documented.
The README notes that if environment variables are not set, the server will not access real Google Sheets and returns mock data. No other limits are stated.

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

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.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
A search tool helps dev to solve the naming things problem.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
Comments