Google Drive MCP Server

by danfeder

411 downloads
Not rated
GitHub

About

Google Drive MCP Server - A Model Context Protocol server for intelligent Google Drive integration with OAuth 2.0, content analysis, and organization insights

Details

Author
danfeder
Downloads
411
Categories
Other, File Management

- List files and folders with advanced filtering and pagination.
- Extract and retrieve file content with metadata.
- Full-text search with relevance scoring and filtering.
- AI-powered content analysis with summarization and categorization.
- Drive organization analysis with actionable recommendations.
- Secure OAuth2 authentication with Google Drive API.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Google Drive MCP Server
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install Node.js 18+, clone the repository, install dependencies, set up Google Cloud OAuth2 credentials, configure environment variables, build and start the server. Then integrate with an MCP client by adding the server configuration (command: node, args: path to server.js).

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "google drive mcp server": {
            "gdrive-sparc-mcp": {
                "command": "node",
                "args": [
                    "test-server.js"
                ]
            }
        }
    }
}

McpServers

{
    "gdrive-sparc-mcp": {
        "command": "node",
        "args": [
            "test-server.js"
        ]
    }
}

Google Drive MCP Server

AI-powered Google Drive integration through Model Context Protocol (MCP) providing intelligent file management, content analysis, and organization insights.

πŸš€ Features

Core MCP Tools

- list_files - List files and folders with advanced filtering and pagination - get_file_content - Extract and retrieve file content with metadata - search_files - Full-text search with relevance scoring and filtering - analyze_content - AI-powered content analysis with summarization and categorization - get_organization_insights - Drive organization analysis with actionable recommendations

Key Capabilities

- πŸ” Secure OAuth2 Authentication with Google Drive API - πŸ“Š Content Analysis - AI-powered summarization, categorization, and keyword extraction - πŸ” Advanced Search - Full-text search with relevance scoring and filtering - πŸ“ Organization Insights - Duplicate detection and structure optimization - ⚑ Performance Optimized - Intelligent caching and rate limiting - πŸ›‘οΈ Production Ready - Comprehensive error handling and logging

πŸ“‹ Prerequisites

- Node.js 18.0.0 or higher
- Google Cloud Project with Drive API enabled
- OAuth2 Credentials from Google Cloud Console

πŸ› οΈ Installation

1. Clone and Install Dependencies

git clone <repository-url>
cd gdrive-sparc-mcp
npm install

2. Google Cloud Setup

1. Create Google Cloud Project
- Go to Google Cloud Console
- Create a new project or select existing one

2. Enable Google Drive API

   # Using gcloud CLI
gcloud services enable drive.googleapis.com

3. Create OAuth2 Credentials
- Navigate to APIs & Services > Credentials
- Click "Create Credentials" > "OAuth 2.0 Client IDs"
- Application type: "Web application"
- Add authorized redirect URI: http://localhost:3000/auth/callback
- Download credentials JSON

3. Environment Configuration

Create .env file from template:

cp .env.example .env

Configure required environment variables:

```env

No reviews yet β€” be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.