Google Sheet MCP Server
Provides tools for reading, writing, and managing Google Sheets, including listing sheets, reading data, creating/renaming/deleting sheets, appending data, adding columns, and deleting rows/columns.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Google Sheet MCP Server
An MCP (Model Context Protocol) server that allows AI agents to read, write, and manage Google Sheets using the Google Sheets API v4.
Features
List Sheets: Retrieve a list of all sheets in a spreadsheet with their names, IDs, and grid properties.
Read Content: Read data from specific sheets or ranges, returned as formatted Markdown tables.
Write Content: API to create sheets, append data, and add columns.
Manage Structure: Rename sheets and delete sheets, columns, or rows.
Related MCP server: mcp-google-sheets
Prerequisites
Python: 3.12 or higher
Package Manager:
uv(recommended) orpipGoogle Cloud Project:
"Google Sheets API" enabled.
Service Account created with a JSON key file.
Access: The Service Account email MUST have "Editor" access to the target Google Sheet to perform write operations.
Getting service-account-key.json
Create Project: Go to Google Cloud Console and create a new project.
Enable API: Search for "Google Sheets API" and click Enable.
Create Service Account:
Go to IAM & Admin > Service Accounts.
Click Create Service Account.
Name it (e.g.,
sheet-mcp-bot) and click Create and Continue.Grant "Editor" role, then click Done.
Generate Key:
Click on the newly created Service Account email.
Go to the Keys tab > Add Key > Create new key.
Select JSON and click Create.
The file will download automatically. Rename it to
service-account-key.json.
Share Sheet: Open your target Google Sheet, click Share, and paste the Service Account email (found in the JSON file under
client_email) with Editor permissions.
Installation
Clone/Open this repository.
Install dependencies:
uv sync # or pip install mcp pandas python-dotenv google-api-python-client google-auth
Configuration
Service Account: Place your Google Service Account JSON key in the project root and name it
service-account-key.json(or update.envto point to its path).Environment Variables: Create a
.envfile:SPREADSHEET_ID=your_spreadsheet_id_here SERVICE_ACCOUNT_FILE=service-account-key.jsonTip: The Spreadsheet ID is the long string in your sheet's URL:
https://docs.google.com/spreadsheets/d/SPREADSHEET_ID/edit
Usage with MCP Clients
Option 1: Using uvx (Recommended)
This method allows you to run the server directly from GitHub without cloning the repository manually.
Add this configuration to your MCP settings file (e.g., claude_desktop_config.json or mcp_config.json):
{
"mcpServers": {
"google-sheet": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/vfh-tech/gsheet-mcp",
"sheet-mcp"
],
"env": {
"SPREADSHEET_ID": "your_spreadsheet_id_here",
"SERVICE_ACCOUNT_FILE": "C:\\path\\to\\your\\service-account-key.json"
}
}
}
}Option 2: Local Installation
If you prefer to clone the repository and run it locally:
{
"mcpServers": {
"google-sheet": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/sheet-mcp",
"run",
"sheet-mcp"
],
"env": {
"SPREADSHEET_ID": "your_spreadsheet_id_here",
"SERVICE_ACCOUNT_FILE": "service-account-key.json"
}
}
}
}Testing
A verification script is included to test the connection and tools:
uv run test_server.pyTools Available
Read Operations
list_sheets(): Lists all sheets in the configured spreadsheet.read_sheet_data(sheet_name: str, range_name: str = None, last_20_rows: bool = False): Reads data from the specified sheet. Setlast_20_rows=Trueto read only the last 20 rows (plus header).
Write Operations
create_sheet(title: str): Creates a new sheet (tab).rename_sheet(old_title: str, new_title: str): Renames an existing sheet.append_data(sheet_name: str, values: List[List[Any]]): Appends rows of data to the bottom of a sheet.add_column(sheet_name: str, header: str, values: List[Any] = None): Adds a new column to the right of the existing data, with an optional header and values.
Delete Operations (Destructive)
delete_sheet(sheet_name: str): Deletes an entire sheet.delete_row(sheet_name: str, start_index: int, end_index: int): Deletes rows within a specified range.delete_column(sheet_name: str, start_index: int, end_index: int): Deletes columns within a specified range.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Connect AI assistants to Google Sheets through controlled tools for reading and updating rows.
Google Sheets via Apify: write Apify datasets or JSON rows to a sheet, or read a sheet as JSON.
Connect an AI assistant to your Google Sheets, Drive, Docs, PDFs, BigQuery and Gmail.
Read and write Google Sheets rows via SheetDB APIs; per-API agent permissions, approved deletes.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to seamlessly interact with Google Sheets through secure OAuth 2.0 authentication. Supports reading, searching, updating spreadsheet data, and managing sheets with smart text replacement and batch operations.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to create, read, update, and manage Google Sheets data and structure using tools like create, listSheets, sheetData, updateCells, and shareSpreadsheet, supporting OAuth2 and service-account authentication.18MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with Google Sheets, performing operations like creating, reading, updating, and clearing spreadsheet data.1MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to read, write, and format Google Sheets using the Google Sheets API v4.1-