mcp-google-sheets
Enables AI assistants to read, write, and manage Google Sheets spreadsheets through natural language commands, providing a bridge between MCP clients and the Google Sheets API.
README
<div align="center"> <b>mcp-google-sheets</b>
<p align="center"> <i>Your AI Assistant's Gateway to Google Sheets! </i>📊 </p>
🤔 What is this?
mcp-google-sheets is a Node.js/TypeScript MCP server that acts as a bridge between any MCP-compatible client (like Claude Desktop) and the Google Sheets API. It allows you to interact with your Google Spreadsheets using a defined set of tools, enabling powerful automation and data manipulation workflows driven by AI.
🚀 Quick Start with OAuth 2.0
The easiest way to get started is using OAuth 2.0 with environment variables - no credential files needed!
1. Prerequisites
- Node.js 18+ installed (download here)
- A Google Cloud Platform account
2. Google Cloud Setup
-
Go to Google Cloud Console
-
Create a new project or select an existing one
-
Enable the following APIs:
- Google Sheets API
- Google Drive API
-
Create OAuth 2.0 Credentials:
- Navigate to APIs & Services → Credentials
- Click + CREATE CREDENTIALS → OAuth client ID
- Choose Desktop app as the application type
- Name it (e.g., "MCP Google Sheets")
- Click CREATE
- Copy the Client ID and Client Secret (you'll need these!)
-
Configure OAuth Consent Screen:
- Go to APIs & Services → OAuth consent screen
- Select External (unless you have a Google Workspace)
- Fill in the required information
- Add the following scopes:
https://www.googleapis.com/auth/spreadsheetshttps://www.googleapis.com/auth/drive.file
- Add your email as a test user
3. Install and Run
# Install globally
npm install -g mcp-google-sheets
# Or run directly with npx (no installation needed)
npx mcp-google-sheets
4. Set Environment Variables
Set your OAuth credentials as environment variables:
Linux/macOS:
export GOOGLE_SHEETS_CLIENT_ID="your-client-id.apps.googleusercontent.com"
export GOOGLE_SHEETS_CLIENT_SECRET="your-client-secret"
export TOKEN_PATH="$HOME/.mcp-google-sheets-token.json"
Windows (PowerShell):
$env:GOOGLE_SHEETS_CLIENT_ID = "your-client-id.apps.googleusercontent.com"
$env:GOOGLE_SHEETS_CLIENT_SECRET = "your-client-secret"
$env:TOKEN_PATH = "$env:USERPROFILE\.mcp-google-sheets-token.json"
Windows (CMD):
set GOOGLE_SHEETS_CLIENT_ID=your-client-id.apps.googleusercontent.com
set GOOGLE_SHEETS_CLIENT_SECRET=your-client-secret
set TOKEN_PATH=%USERPROFILE%\.mcp-google-sheets-token.json
5. First Run (Interactive Authentication)
On the first run, a browser window will open for you to authenticate:
npx mcp-google-sheets
- A browser will open automatically
- Sign in with your Google account
- Grant the requested permissions
- The token will be saved to
TOKEN_PATHfor future use
After the first authentication, the server will use the saved token automatically!
🔌 Usage with Claude Desktop
Add this configuration to your Claude Desktop config file:
Location:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Configuration:
{
"mcpServers": {
"google-sheets": {
"command": "npx",
"args": ["mcp-google-sheets"],
"env": {
"GOOGLE_SHEETS_CLIENT_ID": "your-client-id.apps.googleusercontent.com",
"GOOGLE_SHEETS_CLIENT_SECRET": "your-client-secret",
"TOKEN_PATH": "/full/path/to/token.json"
}
}
}
}
macOS Note: If you get a spawn npx ENOENT error, use the full path:
{
"mcpServers": {
"google-sheets": {
"command": "/usr/local/bin/npx",
"args": ["mcp-google-sheets"],
"env": {
"GOOGLE_SHEETS_CLIENT_ID": "your-client-id.apps.googleusercontent.com",
"GOOGLE_SHEETS_CLIENT_SECRET": "your-client-secret",
"TOKEN_PATH": "/Users/yourusername/.mcp-google-sheets-token.json"
}
}
}
}
🔑 Alternative Authentication Methods
Method A: OAuth 2.0 with Direct Token Injection (For Gemini CLI / Database-backed) 🚀
Pros:
- No token files needed
- Perfect for database-backed OAuth flows
- Automatic token refresh
- Ideal for Gemini CLI integration
Setup:
Set these environment variables with tokens from your database:
export GOOGLE_SHEETS_CLIENT_ID="your-client-id.apps.googleusercontent.com"
export GOOGLE_SHEETS_CLIENT_SECRET="your-client-secret"
export GOOGLE_SHEETS_ACCESS_TOKEN="ya29.a0AfB_byD..."
export GOOGLE_SHEETS_REFRESH_TOKEN="1//0gH..." # Optional but recommended
export GOOGLE_SHEETS_TOKEN_EXPIRY="2025-11-25T10:34:45.248Z" # ISO 8601 format
The server will use these tokens directly without needing any files!
For Gemini CLI users: See GEMINI_CLI_SETUP.md for detailed integration guide.
Method B: OAuth 2.0 with Environment Variables (Interactive) ✅
Pros:
- No credential files to manage
- Easy to configure in CI/CD
- Secure token storage
- Works great for personal use
Setup: See Quick Start above
Method C: Service Account (For Server/Automation) 🤖
Pros:
- No interactive authentication needed
- Great for headless servers
- Can be used in Docker containers
Setup:
- In Google Cloud Console → IAM & Admin → Service Accounts
- Click + CREATE SERVICE ACCOUNT
- Name it and grant necessary roles
- Click Keys → Add Key → Create new key → JSON
- Download the JSON key file
Environment Variables:
export SERVICE_ACCOUNT_PATH="/path/to/service-account-key.json"
export DRIVE_FOLDER_ID="your-google-drive-folder-id" # Optional
Important: Share your Google Drive folder with the service account email (found in the JSON file as client_email)
Method D: OAuth 2.0 with Credentials File (Legacy) 📄
Setup:
- Download OAuth credentials JSON from Google Cloud Console
- Save as
credentials.json
Environment Variables:
export CREDENTIALS_PATH="/path/to/credentials.json"
export TOKEN_PATH="/path/to/token.json"
Method E: Application Default Credentials (ADC) 🌐
For Google Cloud environments (GKE, Cloud Run, etc.)
# Local development
gcloud auth application-default login --scopes=https://www.googleapis.com/auth/spreadsheets,https://www.googleapis.com/auth/drive.file
# Or set the standard Google variable
export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account.json"
🛠️ Available Tools
The server provides these tools for Claude (or any MCP client):
Spreadsheet Operations
list_spreadsheets- List all accessible spreadsheetscreate_spreadsheet- Create a new spreadsheetget_sheet_data- Read data from a sheetupdate_cells- Update cell valuesbatch_update_cells- Update multiple ranges at once
Sheet Management
list_sheets- List all sheets in a spreadsheetcreate_sheet- Add a new sheet tabshare_spreadsheet- Share with users via email
Resources
spreadsheet://{id}/info- Get spreadsheet metadata
💬 Example Prompts for Claude
Once connected, try these prompts:
- "List all my spreadsheets"
- "Create a new spreadsheet called 'Q4 Budget 2024'"
- "Get the data from Sheet1 in my Budget spreadsheet"
- "Update cell A1 in Sheet1 to 'Total Revenue'"
- "Share my Budget spreadsheet with john@example.com as a viewer"
- "Create a new sheet called 'Summary' in my Budget spreadsheet"
🔧 Development
Clone and Build
# Clone the repository
git clone https://github.com/xing5/mcp-google-sheets.git
cd mcp-google-sheets
# Install dependencies
npm install
# Build TypeScript
npm run build
# Run locally
node dist/index.js
Project Structure
mcp-google-sheets/
├── src/
│ ├── index.ts # Main server entry point
│ ├── auth.ts # Authentication logic
│ ├── tools.ts # Tool implementations
│ └── resources.ts # Resource handlers
├── dist/ # Compiled JavaScript
├── package.json
├── tsconfig.json
└── README.md
Testing Locally with Claude Desktop
{
"mcpServers": {
"google-sheets-dev": {
"command": "node",
"args": ["/absolute/path/to/mcp-google-sheets/dist/index.js"],
"env": {
"GOOGLE_SHEETS_CLIENT_ID": "your-client-id",
"GOOGLE_SHEETS_CLIENT_SECRET": "your-client-secret",
"TOKEN_PATH": "/path/to/token.json"
}
}
}
}
🐳 Docker Support
# Build
docker build -t mcp-google-sheets .
# Run with OAuth (requires pre-authenticated token)
docker run -p 8000:8000 \
-e GOOGLE_SHEETS_CLIENT_ID="your-client-id" \
-e GOOGLE_SHEETS_CLIENT_SECRET="your-secret" \
-v /path/to/token.json:/app/token.json \
-e TOKEN_PATH=/app/token.json \
mcp-google-sheets
# Run with Service Account
docker run -p 8000:8000 \
-e SERVICE_ACCOUNT_PATH=/app/service-account.json \
-v /path/to/service-account.json:/app/service-account.json \
mcp-google-sheets
🔒 Security Best Practices
- Never commit credentials to version control
- Use environment variables for sensitive data
- Restrict OAuth scopes to only what you need
- Use Service Accounts for production/automation
- Regularly rotate service account keys
- Store tokens securely with appropriate file permissions
🐛 Troubleshooting
"All authentication methods failed"
Solution: Ensure you've set the required environment variables:
# Check if variables are set
echo $GOOGLE_SHEETS_CLIENT_ID
echo $GOOGLE_SHEETS_CLIENT_SECRET
echo $TOKEN_PATH
"OAuth token not found"
Solution: Run the server interactively first to authenticate:
npx mcp-google-sheets
A browser will open for authentication.
"spawn npx ENOENT" (macOS)
Solution: Use the full path to npx in Claude Desktop config:
which npx # Find the full path
Token expired
Solution: The server automatically refreshes tokens. If issues persist, delete the token file and re-authenticate:
rm ~/.mcp-google-sheets-token.json
npx mcp-google-sheets # Re-authenticate
📝 Environment Variables Reference
| Variable | Required | Description | Default |
|---|---|---|---|
GOOGLE_SHEETS_CLIENT_ID |
For OAuth | OAuth 2.0 Client ID | - |
GOOGLE_SHEETS_CLIENT_SECRET |
For OAuth | OAuth 2.0 Client Secret | - |
GOOGLE_SHEETS_ACCESS_TOKEN |
For Direct Token | OAuth access token from DB | - |
GOOGLE_SHEETS_REFRESH_TOKEN |
For Direct Token | OAuth refresh token (optional) | - |
GOOGLE_SHEETS_TOKEN_EXPIRY |
For Direct Token | Token expiry (ISO 8601) | - |
TOKEN_PATH |
For File-based OAuth | Path to store OAuth token | token.json |
SERVICE_ACCOUNT_PATH |
For Service Account | Path to service account JSON | - |
DRIVE_FOLDER_ID |
Optional | Default Google Drive folder | - |
CREDENTIALS_PATH |
For Legacy OAuth | Path to credentials.json | credentials.json |
GOOGLE_APPLICATION_CREDENTIALS |
For ADC | Google's standard ADC variable | - |
🤝 Contributing
Contributions are welcome! Please:
- Fork the repository
- Create a feature branch
- Make your changes
- Submit a pull request
📄 License
MIT License - see LICENSE file for details
🙏 Credits
- Built with @modelcontextprotocol/sdk
- Uses googleapis
- Inspired by kazz187/mcp-google-spreadsheet
📧 Support
- Issues: GitHub Issues
- Discussions: GitHub Discussions
<div align="center"> Made with ❤️ for the MCP community </div>
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.