mcp-google-sheets

🤔 What is this?

mcp-google-sheets is a Python-based 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 (Using uvx)

Essentially the server runs in one line: uvx mcp-google-sheets.

This cmd will automatically download the latest code if needed and run it. However, it takes quite a few steps to setup the Google Cloud, please read the steps below.

1. ☁️ Prerequisite: Google Cloud Setup
   • You must configure Google Cloud Platform credentials and enable the necessary APIs first. We strongly recommend using a Service Account.
   • ➡️ Jump to the Detailed Google Cloud Platform Setup guide below.
2. 🐍 Install uv
   • uvx is part of uv, a fast Python package installer and resolver. Install it if you haven't already:
     # macOS / Linux curl -LsSf https://astral.sh/uv/install.sh | sh # Windows powershell -c "irm https://astral.sh/uv/install.ps1 | iex" # Or using pip: # pip install uv
     Follow instructions in the installer output to add uv to your PATH if needed.
3. 🔑 Set Essential Environment Variables (Service Account Recommended)
   • You need to tell the server how to authenticate. Set these variables in your terminal:
   • (Linux/macOS)
     # Replace with YOUR actual path and folder ID from the Google Setup step export SERVICE_ACCOUNT_PATH="/path/to/your/service-account-key.json" export DRIVE_FOLDER_ID="YOUR_DRIVE_FOLDER_ID"
   • (Windows CMD)
     set SERVICE_ACCOUNT_PATH="C:\path\to\your\service-account-key.json" set DRIVE_FOLDER_ID="YOUR_DRIVE_FOLDER_ID"
   • (Windows PowerShell)
     $env:SERVICE_ACCOUNT_PATH = "C:\path\to\your\service-account-key.json" $env:DRIVE_FOLDER_ID = "YOUR_DRIVE_FOLDER_ID"
   • ➡️ See Detailed Authentication & Environment Variables for other options (OAuth, CREDENTIALS_CONFIG).
4. 🏃 Run the Server!
   • uvx will automatically download and run the latest version of mcp-google-sheets:
     uvx mcp-google-sheets
   • The server will start and print logs indicating it's ready.
5. 🔌 Connect your MCP Client
   • Configure your client (e.g., Claude Desktop) to connect to the running server.
   • Depending on the client you use, you might not need step 4 because the client can launch the server for you. But it's a good practice to test run step 4 anyway to make sure things are set up properly.
   • ➡️ See Usage with Claude Desktop for examples.

You're ready! Start issuing commands via your MCP client.

✨ Key Features

• Seamless Integration: Connects directly to Google Drive & Google Sheets APIs.
• Comprehensive Tools: Offers a wide range of operations (CRUD, listing, batching, sharing, formatting, etc.).
• Flexible Authentication: Supports Service Accounts (recommended), OAuth 2.0, and direct credential injection via environment variables.
• Easy Deployment: Run instantly with uvx (zero-install feel) or clone for development using uv.
• AI-Ready: Designed for use with MCP-compatible clients, enabling natural language spreadsheet interaction.

🛠️ Available Tools & Resources

This server exposes the following tools for interacting with Google Sheets:

(Input parameters are typically strings unless otherwise specified)

• list_spreadsheets: Lists spreadsheets in the configured Drive folder (Service Account) or accessible by the user (OAuth).
  • Returns: List of objects [{id: string, title: string}]
• create_spreadsheet: Creates a new spreadsheet.
  • title (string): The desired title.
  • Returns: Object with spreadsheet info, including spreadsheetId.
• get_sheet_data: Reads data from a range in a sheet.
  • spreadsheet_id (string)
  • sheet (string): Name of the sheet.
  • range (optional string): A1 notation (e.g., 'A1:C10', 'Sheet1!B2:D'). If omitted, reads the whole sheet.
  • Returns: 2D array of cell values.
• update_cells: Writes data to a specific range. Overwrites existing data.
  • spreadsheet_id (string)
  • sheet (string)
  • range (string): A1 notation.
  • data (2D array): Values to write.
  • Returns: Update result object.
• batch_update_cells: Updates multiple ranges in one API call.
  • spreadsheet_id (string)
  • sheet (string)
  • ranges (object): Dictionary mapping range strings (A1 notation) to 2D arrays of values { "A1:B2": [[1, 2], [3, 4]], "D5": [["Hello"]] }.
  • Returns: Batch update result object.
• add_rows: Appends rows to the end of a sheet (after the last row with data).
  • spreadsheet_id (string)
  • sheet (string)
  • data (2D array): Rows to append.
  • Returns: Update result object.
• list_sheets: Lists all sheet names within a spreadsheet.
  • spreadsheet_id (string)
  • Returns: List of sheet name strings ["Sheet1", "Sheet2"].
• create_sheet: Adds a new sheet (tab) to a spreadsheet.
  • spreadsheet_id (string)
  • title (string): Name for the new sheet.
  • Returns: New sheet properties object.
• get_multiple_sheet_data: Fetches data from multiple ranges across potentially different spreadsheets in one call.
  • queries (array of objects): Each object needs spreadsheet_id, sheet, and range. [{spreadsheet_id: 'abc', sheet: 'Sheet1', range: 'A1:B2'}, ...].
  • Returns: List of objects, each containing the query params and fetched data or an error.
• get_multiple_spreadsheet_summary: Gets titles, sheet names, headers, and first few rows for multiple spreadsheets.
  • spreadsheet_ids (array of strings)
  • rows_to_fetch (optional integer, default 5): How many rows (including header) to preview.
  • Returns: List of summary objects for each spreadsheet.
• share_spreadsheet: Shares a spreadsheet with specified users/emails and roles.
  • spreadsheet_id (string)
  • recipients (array of objects): [{email_address: 'user@example.com', role: 'writer'}, ...]. Roles: reader, commenter, writer.
  • send_notification (optional boolean, default True): Send email notifications.
  • Returns: Dictionary with successes and failures lists.
• add_columns: Adds columns to a sheet. (Verify parameters if implemented)
• copy_sheet: Duplicates a sheet within a spreadsheet. (Verify parameters if implemented)
• rename_sheet: Renames an existing sheet. (Verify parameters if implemented)

MCP Resources:

• spreadsheet://{spreadsheet_id}/info: Get basic metadata about a Google Spreadsheet.
  • Returns: JSON string with spreadsheet information.

☁️ Google Cloud Platform Setup (Detailed)

This setup is required before running the server.

1. Create/Select a GCP Project: Go to the Google Cloud Console.
2. Enable APIs: Navigate to "APIs & Services" -> "Library". Search for and enable:
   • Google Sheets API
   • Google Drive API
3. Configure Credentials: You need to choose one authentication method below (Service Account is recommended).

🔑 Authentication & Environment Variables (Detailed)

The server needs credentials to access Google APIs. Choose one method:

Method A: Service Account (Recommended for Servers/Automation) ✅

• Why? Headless (no browser needed), secure, ideal for server environments. Doesn't expire easily.
• Steps:
  1. Create Service Account: In GCP Console -> "IAM & Admin" -> "Service Accounts".
     • Click "+ CREATE SERVICE ACCOUNT". Name it (e.g., mcp-sheets-service).
     • Grant Roles: Add Editor role for broad access, or more granular roles (like roles/drive.file and specific Sheets roles) for stricter permissions.
     • Click "Done". Find the account, click Actions (⋮) -> "Manage keys".
     • Click "ADD KEY" -> "Create new key" -> JSON -> "CREATE".
     • Download and securely store the JSON key file.
  2. Create & Share Google Drive Folder:
     • In Google Drive, create a folder (e.g., "AI Managed Sheets").
     • Note the Folder ID from the URL: https://drive.google.com/drive/folders/THIS_IS_THE_FOLDER_ID.
     • Right-click the folder -> "Share" -> "Share".
     • Enter the Service Account's email (from the JSON file client_email).
     • Grant Editor access. Uncheck "Notify people". Click "Share".
  3. Set Environment Variables:
     • SERVICE_ACCOUNT_PATH: Full path to the downloaded JSON key file.
     • DRIVE_FOLDER_ID: The ID of the shared Google Drive folder. (See Ultra Quick Start for OS-specific examples)

Method B: OAuth 2.0 (Interactive / Personal Use) 🧑‍💻

• Why? For personal use or local development where interactive browser login is okay.
• Steps:
  1. Configure OAuth Consent Screen: In GCP Console -> "APIs & Services" -> "OAuth consent screen". Select "External", fill required info, add scopes (.../auth/spreadsheets, .../auth/drive), add test users if needed.
  2. Create OAuth Client ID: In GCP Console -> "APIs & Services" -> "Credentials". "+ CREATE CREDENTIALS" -> "OAuth client ID" -> Type: Desktop app. Name it. "CREATE". Download JSON.
  3. Set Environment Variables:
     • CREDENTIALS_PATH: Path to the downloaded OAuth credentials JSON file (default: credentials.json).
     • TOKEN_PATH: Path to store the user's refresh token after first login (default: token.json). Must be writable.

Method C: Direct Credential Injection (Advanced) 🔒

• Why? Useful in environments like Docker, Kubernetes, or CI/CD where managing files is hard, but environment variables are easy/secure. Avoids file system access.
• How? Instead of providing a path to the credentials file, you provide the content of the file, encoded in Base64, directly in an environment variable.
• Steps:
  1. Get your credentials JSON file (either Service Account key or OAuth Client ID file). Let's call it your_credentials.json.
  2. Generate the Base64 string:
     • (Linux/macOS): base64 -w 0 your_credentials.json
     • (Windows PowerShell):
       $filePath = "C:\path\to\your_credentials.json"; # Use actual path $bytes = [System.IO.File]::ReadAllBytes($filePath); $base64 = [System.Convert]::ToBase64String($bytes); $base64 # Copy this output
     • (Caution): Avoid pasting sensitive credentials into untrusted online encoders.
  3. Set the Environment Variable:
     • CREDENTIALS_CONFIG: Set this variable to the full Base64 string you just generated.
       # Example (Linux/macOS) - Use the actual string generated export CREDENTIALS_CONFIG="ewogICJ0eXBlIjogInNlcnZpY2VfYWNjb..."

Authentication Priority & Summary

The server checks for credentials in this order:

1. CREDENTIALS_CONFIG (Base64 content)
2. SERVICE_ACCOUNT_PATH (Path to Service Account JSON)
3. CREDENTIALS_PATH (Path to OAuth JSON) - triggers interactive flow if token is missing/expired.

Environment Variable Summary:

⚙️ Running the Server (Detailed)

Method 1: Using uvx (Recommended for Users)

As shown in the Ultra Quick Start, this is the easiest way. Set environment variables, then run:

uvx handles fetching and running the package temporarily.

Method 2: For Development (Cloning the Repo)

If you want to modify the code:

1. Clone: git clone https://github.com/yourusername/mcp-google-sheets.git && cd mcp-google-sheets (Use actual URL)
2. Set Environment Variables: As described above.
3. Run using uv: (Uses the local code)
   uv run mcp-google-sheets # Or via the script name if defined in pyproject.toml, e.g.: # uv run start

🔌 Usage with Claude Desktop

Add the server config to claude_desktop_config.json under mcpServers. Choose the block matching your setup:

(A browser may open for Google login on first use)

💬 Example Prompts for Claude

Once connected, try prompts like:

• "List all spreadsheets I have access to." (or "in my AI Managed Sheets folder")
• "Create a new spreadsheet titled 'Quarterly Sales Report Q3 2024'."
• "In the 'Quarterly Sales Report' spreadsheet, get the data from Sheet1 range A1 to E10."
• "Add a new sheet named 'Summary' to the spreadsheet with ID 1aBcDeFgHiJkLmNoPqRsTuVwXyZ."
• "In my 'Project Tasks' spreadsheet, Sheet 'Tasks', update cell B2 to 'In Progress'."
• "Append these rows to the 'Log' sheet in spreadsheet XYZ: [['2024-07-31', 'Task A Completed'], ['2024-08-01', 'Task B Started']]"
• "Get a summary of the spreadsheets 'Sales Data' and 'Inventory Count'."
• "Share the 'Team Vacation Schedule' spreadsheet with team@example.com as a reader and manager@example.com as a writer. Don't send notifications."

🤝 Contributing

Contributions are welcome! Please open an issue to discuss bugs or feature requests. Pull requests are appreciated.

📄 License

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

🙏 Credits

• Built with FastMCP.
• Inspired by kazz187/mcp-google-spreadsheet.
• Uses Google API Python Client libraries.