## 🎉 New Feature: Direct Google JSON Field Names
 
 ### ✨ What's New:
 - **Copy-paste friendly**: Use exact Google JSON field names
 - **No more `GOOGLE_` prefix**: Direct field mapping
 - **Backward compatibility**: Old format still supported
 
 ### 🔧 Configuration:
 ```json
 {
   "env": {
     "project_id": "your-project-id",
     "private_key_id": "your-private-key-id", 
     "private_key": "-----BEGIN PRIVATE KEY-----\n...\n-----END PRIVATE KEY-----\n",
     "client_email": "[email protected]",
     "client_id": "your-client-id",
     "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/your-service%40your-project.iam.gserviceaccount.com"
   }
 }
 ```
 
 ### 🚀 Benefits:
 - Users can copy directly from Google service account JSON
 - No manual field name modifications needed
 - Easier setup process
 - Maintains backward compatibility

Bug Fixes

• Fixed package structure by moving main.py into the package
• Updated entry point to use proper package path
• Fixed all hardcoded version references in workflows
• Corrected syntax errors in version extraction commands
• Fixed Python compatibility (regex instead of toml/tomllib)
• Added virtual environment creation to GitHub Actions
• Made version checks dynamic across all files
• Improved package installation and execution

Full Changelog: https://github.com/henilcalagiya/google-sheets-mcp/compare/v0.1.2...v0.1.3

Bug Fixes

• Fixed main.py inclusion in wheel package
• Improved error handling for package imports
• Better user experience when running directly

Full Changelog: https://github.com/henilcalagiya/google-sheets-mcp/compare/v0.1.1...v0.1.2

Bug Fixes

• Fixed main.py execution when running with uvx
• Improved error handling for package imports
• Better user experience when running directly

Full Changelog: https://github.com/henilcalagiya/google-sheets-mcp/compare/v0.1.0...v0.1.1

Google Sheets MCP Server

Powerful tools for automating Google Sheets using Model Context Protocol (MCP)

Overview

Google Sheets MCP Server provides seamless integration of Google Sheets with any MCP-compatible client. It enables full spreadsheet automation — including creating, reading, updating, and deleting sheets — through a simple and secure API layer.

Features

• Full CRUD support for Google Sheets and tables
• Works with Continue.dev, Claude Desktop, Perplexity, and other MCP clients
• Secure authentication via Google Service Account
• Comprehensive tools for Google Sheets automation
• Automatic installation via uvx

Requirements

• Python 3.10+
• uv package manager (for uvx command)
• A Google Cloud project with a Service Account
• MCP-compatible client (e.g., Continue.dev)

Install uv:

# macOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows PowerShell
irm https://astral.sh/uv/install.ps1 | iex

Quick Start

1. Set Up Google Service Account

Step 1: Create a Google Cloud Project

1. Go to Google Cloud Console
2. Click "Select a project" → "New Project"
3. Enter a project name (e.g., "my-sheets-automation")
4. Click "Create"

Step 2: Enable Required APIs

1. In your project, go to "APIs & Services" → "Library"
2. Search for "Google Sheets API" → Click → "Enable"
3. Search for "Google Drive API" → Click → "Enable"

Step 3: Create Service Account

1. Go to "IAM & Admin" → "Service Accounts"
2. Click "Create Service Account"
3. Enter service account name (e.g., "sheets-mcp-service")
4. Click "Create and Continue"
5. Skip role assignment → Click "Continue"
6. Click "Done"

Step 4: Generate JSON Key

1. Click on your new service account email
2. Go to "Keys" tab → "Add Key" → "Create new key"
3. Choose "JSON" format → Click "Create"
4. The JSON file will download automatically

Step 5: Extract Required Values
Open the downloaded JSON file and note these values:

• project_id (e.g., "my-sheets-automation-123456")
• private_key (the long private key starting with "-----BEGIN PRIVATE KEY-----")
• client_email (e.g., "sheets-mcp-service@my-sheets-automation-123456.iam.gserviceaccount.com")

Follow this guide if needed

2. Configure MCP Client

{
  "mcpServers": {
    "google-sheets-mcp": {
      "command": "uvx",
      "args": ["google-sheets-mcp@latest"],
      "env": {
        "GOOGLE_PROJECT_ID": "your-project-id",
        "GOOGLE_PRIVATE_KEY": "-----BEGIN PRIVATE KEY-----\n...\n-----END PRIVATE KEY-----\n",
        "GOOGLE_CLIENT_EMAIL": "[email protected]"
      }
    }
  }
}

Extract these values from your Google service account JSON file:

• project_id → GOOGLE_PROJECT_ID
• private_key → GOOGLE_PRIVATE_KEY
• client_email → GOOGLE_CLIENT_EMAIL

3. Share Your Google Sheet with the Service Account

• Open your target Google Spreadsheet in your web browser.
• Click the Share button.
• Enter the service account email (e.g., [email protected]) and assign Editor access.
• Click Send to provide editor permissions.

🎉 You're all set! Your MCP client will automatically install and run the package when needed.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Author

Henil C Alagiya

• GitHub: @henilcalagiya
• LinkedIn: Henil C Alagiya

Support & Contributions:

• 🐛 Report Issues: GitHub Issues
• 💬 Questions: Reach out on LinkedIn
• 🤝 Contributions: Pull requests welcome!

Full Changelog: https://github.com/henilcalagiya/google-sheets-mcp/commits/v0.1.0