Google Sheets MCP Server
The Google Sheets MCP server connects AI agents to your Google Spreadsheets. Agents can create spreadsheets, read and write cell ranges and values, append rows, manage sheets and tabs, apply formatting, build charts and tables, and run analysis — letting assistants automate data entry, reporting, and spreadsheet manipulation.
Install Google Sheets
- Published by
- Official (vendor)
- Transport
- Remote (HTTP)
- Authentication
- OAuth
Claude Desktop, Claude Code and Cursor
Add this to the mcpServers object in your client's
config file, then restart the client.
{
"mcpServers": {
"google-sheets": {
"type": "http",
"url": "https://sheetsmcp.googleapis.com/mcp/v1"
}
}
}
VS Code uses a different key — show that config
Identical entry, filed under servers rather than
mcpServers. Put it in
.vscode/mcp.json for one workspace.
{
"servers": {
"google-sheets": {
"type": "http",
"url": "https://sheetsmcp.googleapis.com/mcp/v1"
}
}
}
Before it will answer
Google's Workspace MCP servers are NOT paste-and-go — this is the step people miss. You supply your own OAuth 2.0 client, created in the Google Cloud console as a Web application, and the redirect URI is client-specific (Claude uses https://claude.ai/api/mcp/auth_callback; Antigravity uses https://antigravity.google/oauth-callback). You must also enable TWO services in the project, not one: the product API and its separate MCP service. Here that is sheets.googleapis.com and sheetsmcp.googleapis.com. Consent-screen scopes: drive.readonly, drive.file, spreadsheets.readonly and spreadsheets — grant only the read pair if the agent has no business writing to your spreadsheets.