TNTM Google Sheets Analytics MCP Server
A clean, practical MCP (Model Context Protocol) server for analyzing Google Sheets data with multi-tab support. Built for Claude Desktop and other MCP-compatible AI assistants by TNTM.
🚀 Features
- Smart Sync - Sync Google Sheets with configurable row limits to prevent timeouts
- Multi-tab Support - Query across multiple sheets with SQL JOINs
- SQL Queries - Direct SQL access to synced data
- Sheet Analysis - Get suggestions for cross-sheet queries
- Quick Preview - Preview sheets without full sync
- Performance Optimized - Row limits and result pagination for large datasets
📋 Prerequisites
- Python 3.8+
- Claude Desktop or another MCP-compatible client
- Google Cloud Project with Sheets API enabled
- OAuth2 credentials from Google Cloud Console
🛠️ Setup
1. Clone and Install
2. Google Cloud Setup
- Go to Google Cloud Console
- Create a new project or select existing one
- Enable the Google Sheets API
- Create OAuth2 credentials (Desktop Application)
- Download the credentials and save as
credentials.json
in the project root
3. Run Automated Setup
This will:
- Set up OAuth authentication
- Configure Claude Desktop automatically
- Test the connection
Or configure MCP client manually:
4. First Run
Restart your MCP client (e.g., Claude Desktop) and the OAuth flow will start automatically on first tool use.
🔧 Tools
smart_sync
Sync Google Sheet data with performance controls.
url
(required): Google Sheets URLmax_rows
(optional): Max rows per sheet (default: 1000)sheets
(optional): Array of specific sheet names to sync
query_sheets
Run SQL queries on synced data, including JOINs across tabs.
query
(required): SQL query to execute
list_synced_sheets
View all synced sheets and their table names.
analyze_sheets
Get suggestions for queries across multiple sheets.
question
(required): What you want to analyze
get_sheet_preview
Quick preview without syncing.
url
(required): Google Sheets URLsheet_name
(optional): Specific sheet to previewrows
(optional): Number of rows to preview (default: 10)
📊 How It Works
- Authentication - Uses OAuth2 to securely access Google Sheets API
- Sync - Downloads sheet data to local SQLite database with configurable limits
- Query - Enables SQL queries across all synced sheets
- Multi-tab - Each sheet becomes a separate table, joinable via SQL
🏗️ Project Structure
⚡ Performance
- Row Limits: Default 1000 rows per sheet (configurable)
- Result Limits: Query results limited to 100 rows
- Local Storage: SQLite database for fast repeated queries
- Metadata Tracking: Efficient re-syncing of changed data
- Memory Efficient: Streaming data processing
🔍 Example Use Cases
Multi-tab Analysis
Cross-sheet Aggregation
🔒 Security
- OAuth2 authentication with Google
- Credentials stored locally (never committed to repo)
- Read-only access to Google Sheets
- Local SQLite database (no external data transmission)
🐛 Troubleshooting
Common Issues
Issue | Solution |
---|---|
"No credentials found" | Ensure credentials.json exists in project root or config/ directory |
"Authentication failed" | Check token status with venv/bin/python src/auth/oauth_setup.py --status |
"Token expired" | Run venv/bin/python src/auth/oauth_setup.py --test (auto-refreshes) |
"Sync timeout" | Reduce max_rows parameter in smart_sync |
"Tools not appearing" | Restart Claude Desktop after configuration |
"Rate limit errors" | Wait a few minutes and try again with smaller batches |
OAuth Troubleshooting
- Check status:
venv/bin/python src/auth/oauth_setup.py --status
- Test auth:
venv/bin/python src/auth/oauth_setup.py --test
- Reset OAuth:
venv/bin/python src/auth/oauth_setup.py --reset
- Manual setup:
venv/bin/python src/auth/oauth_setup.py --manual
MCP Server Not Appearing
- Ensure Claude Desktop is fully closed
- Verify config:
cat ~/Library/Application\ Support/Claude/claude_desktop_config.json
- Check the config includes the google-sheets-analytics server
- Restart Claude Desktop
- Check developer console for errors
Database Issues
- Database location:
data/sheets_data.sqlite
- Reset database: Delete the file and re-sync
- Check synced sheets: Use the
list_synced_sheets
tool
🤝 Contributing
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature
) - Commit your changes (
git commit -m 'Add amazing feature'
) - Push to the branch (
git push origin feature/amazing-feature
) - Open a Pull Request
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🙏 Acknowledgments
- Built for the Model Context Protocol
- Designed for Claude Desktop
- Uses Google Sheets API
Need help? Open an issue on GitHub or check the troubleshooting section above.
This server cannot be installed
This MCP server enables AI assistants to automatically sync Google Sheets data to a local database and perform natural language queries and analysis on spreadsheet data.