Overview

The MCP Google Drive Server provides seamless integration with Google Drive, allowing AI models to search, list, and read files from Google Drive. It intelligently handles different Google Workspace file types, converting them to appropriate formats for AI consumption.

Created by:

Developed by felores

Key Features

🔍

Powerful File Search

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

📄

Direct File Content Access

Read file contents directly using a Google Drive file ID.

🔄

Automatic Format Handling

Intelligently converts Google Docs to Markdown, Sheets to CSV, and more.

🔒

Secure Authentication

Secure OAuth 2.0 authentication flow with read-only access.

Available Tools

Quick Reference

Tool	Purpose	Category
`gdrive_search`	Search for files in Google Drive	Discovery
`gdrive_read_file`	Read file contents by ID	Read

Detailed Usage

gdrive_search▶

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

use_mcp_tool({
  server_name: "gdrive",
  tool_name: "gdrive_search",
  arguments: {
    query: "quarterly report"
  }
});

Returns a list of files with name, MIME type, ID, last modified time, and size.

gdrive_read_file▶

Read file contents directly using a Google Drive file ID.

use_mcp_tool({
  server_name: "gdrive",
  tool_name: "gdrive_read_file",
  arguments: {
    file_id: "your-file-id"
  }
});

Returns the file contents with appropriate format conversion (e.g., Docs to Markdown).

Installation

{
  "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"
      }
    }
  }
}

Local Installation:

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

Authentication

To set up authentication for the Google Drive MCP Server, you need to:

Create a Google Cloud Project and enable the Google Drive API.
Configure the OAuth Consent Screen.
Create OAuth Client ID for a "Desktop app" and download the JSON file (e.g., client_secret_*.json).
Create a credentials directory in your gdrive-mcp-server installation.
Move and rename the downloaded JSON file to credentials/gcp-oauth.keys.json.
Run the authentication command: node dist/index.js auth from the server's directory and complete the OAuth flow in your browser. This will generate .gdrive-server-credentials.json.

Common Use Cases

1. Searching for Documents

Find specific documents based on keywords:

use_mcp_tool({
  server_name: "gdrive",
  tool_name: "gdrive_search",
  arguments: {
    query: "meeting minutes Q3 2023"
  }
});

2. Retrieving File Content

Get the content of a Google Doc or other file by its ID:

use_mcp_tool({
  server_name: "gdrive",
  tool_name: "gdrive_read_file",
  arguments: {
    file_id: "1AbCdEfGhIjKlMnOpQrStUvWxYz"
  }
});

3. Processing Google Sheets Data

Read a Google Sheet and process its CSV content:

// Assuming gdrive_read_file returns CSV for Sheets
use_mcp_tool({
  server_name: "gdrive",
  tool_name: "gdrive_read_file",
  arguments: {
    file_id: "your-spreadsheet-id"
  }
});

Sources

Puppeteer MCP Server

Puppeteer MCP servers enable AI models to perform browser automation, web scraping, testing workflows, and screenshot generation through headless Chrome/Chromium control.

Vectara MCP Server

Vectara MCP servers enable AI models to interact with Vectara's RAG platform, providing capabilities for fast and reliable Retrieval-Augmented Generation, semantic search, and hallucination correction.

Datadog MCP Server

Datadog MCP servers enable AI models to interact with Datadog observability: metrics, logs, traces, monitors, dashboards, incidents, and infrastructure insights.

Google Drive MCP Server