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 Code and other MCP-compatible AI assistants by TNTM.
Potencialize seu agente
Instalação do publicador. Não é um endpoint do PlugMCP.
Host a copy with our keys and logs.
Ainda não há uma versão empacotada no registro. Siga o README do repositório.
URL remota ou um comando na sua máquina? Como as duas instalações diferem
Rodar no PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
AbrirDo publicador

A clean, practical MCP (Model Context Protocol) server for analyzing Google Sheets data with multi-tab support. Built for Claude Code and other MCP-compatible AI assistants by TNTM.
Transform Google Sheets into a conversational database. Ask questions like "What are the top 10 customers by revenue?" and get instant SQL-powered insights through any MCP-compatible AI assistant.
credentials.json in the project rootThat's it! Claude Code will handle virtual environments, dependencies, and OAuth setup automatically.
For non-Claude Code users or manual setup:
# Download and run the automated installer
curl -sSL https://raw.githubusercontent.com/yourusername/google-sheet-analytics-mcp/main/install.sh | bash
# Or clone first, then run
git clone https://github.com/yourusername/google-sheet-analytics-mcp.git
cd google-sheet-analytics-mcp
./install.sh
# Clone the repository
git clone https://github.com/yourusername/google-sheet-analytics-mcp.git
cd google-sheet-analytics-mcp
# Run the Python installer
python3 setup.py
# 1. Create virtual environment
python3 -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# 2. Install dependencies
pip install -e .
# 3. Install MCP server
mcp install src/mcp_server.py --name google-sheets-analytics --with-editable .
# 4. Setup OAuth (after adding credentials.json)
python src/auth/oauth_setup.py
Before first use, you need OAuth2 credentials:
credentials.json in the project rootAfter adding your credentials.json file, run the OAuth setup:
python src/auth/oauth_setup.py
This will:
token.json file with your access credentialsYou only need to do this once! After setup, all MCP tools will work automatically.
smart_syncSync Google Sheet data with intelligent chunking for large datasets.
Use smart_sync with url "https://docs.google.com/spreadsheets/d/your_sheet_id" and max_rows 100000
url (required): Google Sheets URLmax_rows (optional): Max rows per sheet (default: 100000, supports up to 1M+)sheets (optional): Array of specific sheet names to syncAuto-scaling behavior:
query_sheetsRun SQL queries on synced data, including JOINs across tabs.
Use query_sheets with query "SELECT * FROM sheet1 JOIN sheet2 ON sheet1.id = sheet2.id LIMIT 10"
query (required): SQL query to executelist_synced_sheetsView all synced sheets and their table names.
Use list_synced_sheets
analyze_sheetsGet suggestions for queries across multiple sheets.
Use analyze_sheets with question "How can I combine sales data with customer data?"
question (required): What you want to analyzeget_sheet_previewQuick preview without syncing.
Use get_sheet_preview with url "https://docs.google.com/spreadsheets/d/your_sheet_id" and rows 20
url (required): Google Sheets URLsheet_name (optional): Specific sheet to previewrows (optional): Number of rows to preview (default: 10)google-sheet-analytics-mcp/
├── src/
│ ├── mcp_server.py # Main MCP server implementation
│ └── auth/
│ └── oauth_setup.py # OAuth authentication module
├── pyproject.toml # Modern Python package configuration
├── credentials.json.example # Example OAuth credentials format
├── README.md # This file
├── LICENSE # MIT License
├── CLAUDE.md # Claude-specific instructions
└── data/ # Runtime data (created automatically)
├── token.json # OAuth token (created during setup)
└── sheets_data.sqlite # Local database (created on first sync)
-- Combine sales data with customer information
SELECT
s.product_name,
s.sales_amount,
c.customer_name,
c.customer_segment
FROM sales_data s
JOIN customer_data c ON s.customer_id = c.id
WHERE s.sales_amount > 1000
-- Total revenue by region from multiple sheets
SELECT
region,
SUM(amount) as total_revenue
FROM (
SELECT region, amount FROM q1_sales
UNION ALL
SELECT region, amount FROM q2_sales
)
GROUP BY region
ORDER BY total_revenue DESC
venv/bin/python src/auth/oauth_setup.py --statusvenv/bin/python src/auth/oauth_setup.py --testvenv/bin/python src/auth/oauth_setup.py --resetvenv/bin/python src/auth/oauth_setup.py --manualcat ~/.config/claude-code/config.jsondata/sheets_data.sqlitelist_synced_sheets toolgit checkout -b feature/amazing-feature)git commit -m 'Add amazing feature')git push origin feature/amazing-feature)This project is licensed under the MIT License - see the LICENSE file for details.
Need help? Open an issue on GitHub or check the troubleshooting section above.
Transform Google Sheets into a conversational database. Ask questions like "What are the top 10 customers by revenue?" and get instant SQL-powered insights through any MCP-compatible AI assistant.
Ferramentas
Ainda não há lista de ferramentas. Servidores remotos recebem uma após a primeira verificação de saúde.
Perguntas frequentes
Copie nesta página a configuração stdio para Cursor, Claude Desktop, Claude Code ou VS Code. Ela usa a instalação do publicador, não um proxy do PlugMCP.
Este registro não lista nenhuma variável de ambiente obrigatória.
Google Sheet Analytics roda localmente via stdio.
Última verificação: 2026-10-28. Transform Google Sheets into a conversational database. Ask questions like "What are the top 10 customers by revenue?" and get instant SQL-powered insights through any MCP-compatible AI assistant.