mcp-registry/mcp-google-sheets

    ==================
      
       /// MCP ///
      /// MCP ///
        
    ==================
        
    [server:online]
    [protocol:ready]

mcp-google-sheets

by xing5

Python MCP server that exposes a rich set of tools for manipulating Google Sheets/Drive via Google APIs so any MCP-compatible client (e.g. Claude Desktop) can read, write, share and manage spreadsheets through natural-language commands.

271
63
Open Source
GitHub

Installation

1. Prerequisites
• Python 3.9+
• A Google Cloud project with both “Google Sheets API” and “Google Drive API” enabled.
2. Clone the repository
git clone https://github.com/xing5/mcp-google-sheets.git cd mcp-google-sheets
3. Create & activate a virtual-environment (recommended)
python -m venv .venv source .venv/bin/activate # Windows: .venv\Scripts\activate
4. Install Python dependencies
pip install -r requirements.txt # or directly from GitHub without cloning: # pip install git+https://github.com/xing5/mcp-google-sheets.git
5. Obtain Google credentials
• In Google Cloud Console create an "OAuth Client ID" (Desktop type).
• Download the JSON file (client_secret_*.json).
• Save it inside the project directory (or any safe location).
• Export the path so the SDK can locate it:
export GOOGLE_APPLICATION_CREDENTIALS="/absolute/path/client_secret.json"
6. First-time authentication
python tools/auth_flow.py # Opens browser, prompts for consent, saves token.json
7. Run the MCP server
python -m mcp_google_sheets.server --host 0.0.0.0 --port 8080
8. Reverse-proxy (optional)
If you need HTTPS, place Nginx/Caddy/Traefik in front and proxy to 127.0.0.1:8080. The server is now reachable by any MCP client.

Documentation

License: MIT License
Updated 7/15/2025