Google Drive MCP Server

A powerful Model Context Protocol (MCP) server that provides seamless integration with Google Drive, allowing AI models to search, list, and read files from Google Drive.

🚀 Features

Tools

1. `gdrive_search`

Search for files in your Google Drive with powerful full-text search capabilities.

• Input:

{
    "query": "string (your search query)"
  }

• Output: List of files with:
  • File name
  • MIME type
  • File ID
  • Last modified time
  • File size

2. `gdrive_read_file`

Read file contents directly using a Google Drive file ID.

• Input:

{
    "file_id": "string (Google Drive file ID)"
  }

• Output: File contents with appropriate format conversion

Automatic File Format Handling

The server intelligently handles different Google Workspace file types:

• 📝 Google Docs → Markdown
• 📊 Google Sheets → CSV
• 📊 Google Presentations → Plain text
• 🎨 Google Drawings → PNG
• 📄 Text/JSON files → UTF-8 text
• 📦 Other files → Base64 encoded

🛠️ Getting Started

Prerequisites

• Node.js (v16 or higher)
• npm or yarn
• A Google Cloud Project
• A Google Workspace or personal Google account

Detailed Google Cloud Setup

1. Create a Google Cloud Project

2. Enable the Google Drive API

3. Configure OAuth Consent Screen

4. Create OAuth Client ID

5. Set Up Credentials in Project

# Create credentials directory
   mkdir credentials
   
   # Move and rename the downloaded JSON file
   mv path/to/downloaded/client_secret_*.json credentials/gcp-oauth.keys.json

Installation

# Clone the repository
git clone https://github.com/felores/gdrive-mcp-server.git
cd gdrive-mcp-server

# Install dependencies
npm install

# Build the project
npm run build

Authentication

1. Create a credentials directory and place your OAuth keys:

mkdir credentials
   # Move your downloaded OAuth JSON file to the credentials directory as gcp-oauth.keys.json

2. Run the authentication command:

node dist/index.js auth

3. Complete the OAuth flow in your browser

4. Credentials will be saved in `credentials/.gdrive-server-credentials.json`

🔧 Usage

As a Command Line Tool

# Start the server
node dist/index.js

Integration with Desktop App

Add this configuration to your app's server settings:

{
  "mcpServers": {
    "gdrive": {
      "command": "node",
      "args": ["path/to/gdrive-mcp-server/dist/index.js"],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "path/to/gdrive-mcp-server/credentials/gcp-oauth.keys.json",
        "MCP_GDRIVE_CREDENTIALS": "path/to/gdrive-mcp-server/credentials/.gdrive-server-credentials.json"
      }
    }
  }
}

Replace `path/to/gdrive-mcp-server` with the actual path to your installation directory.

Example Usage

1. Search for files:

// Search for documents containing "quarterly report"
   const result = await gdrive_search({ query: "quarterly report" });

2. Read file contents:

// Read a specific file using its ID
   const contents = await gdrive_read_file({ file_id: "your-file-id" });

🔒 Security

• All sensitive credentials are stored in the `credentials` directory
• OAuth credentials and tokens are excluded from version control
• Read-only access to Google Drive
• Secure OAuth 2.0 authentication flow

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

📝 License

This MCP server is licensed under the MIT License. See the LICENSE file for details.

🔍 Troubleshooting

If you encounter issues:

1. Verify your Google Cloud Project setup

2. Ensure all required OAuth scopes are enabled

3. Check that credentials are properly placed in the `credentials` directory

4. Verify file permissions and access rights in Google Drive

📚 Additional Resources

• Google Drive API Documentation
• OAuth 2.0 for Desktop Apps
• Model Context Protocol Documentation