
google sheets mcp server
A Model Context Protocol (MCP) server implementation for Google Sheets
Repository Info
About This Server
A Model Context Protocol (MCP) server implementation for Google Sheets
Model Context Protocol (MCP) - This server can be integrated with AI applications to provide additional context and capabilities, enabling enhanced AI interactions and functionality.
Documentation
Google Sheets MCP Server
A Model Context Protocol (MCP) server for Google Sheets that enables Claude Desktop to interact with Google Sheets directly. This server provides tools for creating, reading, writing, and managing Google Sheets through Claude Desktop.
Features
- Create new Google Sheets
- Read and write data to existing sheets
- Format cells and ranges
- Add and delete sheets
- Write formulas
- Search for sheets
- List available sheets
Prerequisites
- Python 3.10 or higher
- Google Cloud Project with Google Sheets API enabled
- OAuth 2.0 credentials from Google Cloud Console
- Claude Desktop application
uvpackage manager (recommended)
Installation
- Clone the repository:
git clone https://github.com/yourusername/google-sheets-mcp-server.git
cd google-sheets-mcp-server
- Create and activate a virtual environment:
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
- Install dependencies using
uv:
uv pip install -e .
- Set up Google Cloud credentials:
- Go to Google Cloud Console
- Create a new project or select an existing one
- Enable the Google Sheets API and Google Drive API
- Create OAuth 2.0 credentials (Desktop app)
- Download the credentials and save as
~/.config/google_sheets_mcp/google-sheets-mcp.json
Configuration
- Configure Claude Desktop:
- Open Claude Desktop settings
- Add the following to your
claude_desktop_config.json:
{
"mcpServers": {
"google_sheets": {
"command": "/path/to/your/.venv/bin/python",
"args": [
"/path/to/your/google_sheets.py",
"--credentials-path",
"/Users/yourusername/.config/google_sheets_mcp/google-sheets-mcp.json",
"--log-level",
"DEBUG"
]
}
}
}
- First-time setup:
- Run the server manually to complete OAuth authentication:
python google_sheets.py --credentials-path ~/.config/google_sheets_mcp/google-sheets-mcp.json
- Follow the browser prompts to authorize the application
- The token will be saved automatically for future use
Usage
After setup, you can use the following commands in Claude Desktop:
- Create a new sheet:
create_sheet(title: str) - Format cells:
format_range(file_id: str, range: str, format: dict) - Write formulas:
write_formula(file_id: str, range: str, formula: str) - Add sheets:
add_sheet(file_id: str, title: str) - Delete sheets:
delete_sheet(file_id: str, sheet_id: int) - Get sheet properties:
get_sheet_properties(file_id: str)
Development
Project Structure
google-sheets-mcp-server/
├── .venv/ # Virtual environment
├── google_sheets.py # Main server implementation
├── pyproject.toml # Project configuration and dependencies
├── tests/ # Test files
└── README.md # This file
Adding New Features
- Add new tool methods to the
GoogleSheetsMCPclass - Decorate them with
@mcp.tool() - Update the README with new feature documentation
Running Tests
pytest
Troubleshooting
-
Server Connection Issues
- Check if the server is running
- Verify credentials path in config
- Check logs in Claude Desktop
-
Authentication Issues
- Ensure OAuth credentials are valid
- Check if your email is added as a test user
- Try deleting token.json and re-authenticating
-
API Errors
- Verify Google Sheets API is enabled
- Check API quotas and limits
- Review error logs for specific issues
Contributing
- Fork the repository
- Create a feature branch
- Commit your changes
- Push to the branch
- Create a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
Quick Start
Clone the repository
git clone https://github.com/amaboh/google-sheets-mcp-serverInstall dependencies
cd google-sheets-mcp-server
npm installFollow the documentation
Check the repository's README.md file for specific installation and usage instructions.
Repository Details
Recommended MCP Servers
Discord MCP
Enable AI assistants to seamlessly interact with Discord servers, channels, and messages.
Knit MCP
Connect AI agents to 200+ SaaS applications and automate workflows.
Apify MCP Server
Deploy and interact with Apify actors for web scraping and data extraction.
BrowserStack MCP
BrowserStack MCP Server for automated testing across multiple browsers.
Zapier MCP
A Zapier server that provides automation capabilities for various apps.