Agentifact assessment — independently scored, not sponsored. Last verified Mar 6, 2026.
Google Drive MCP
Official Google Drive MCP server. Search, read, and manage files. Requires Google OAuth setup.
Viable option — review the tradeoffs
You need your autonomous agents to dynamically search, read, and manage files in Google Drive without custom API wrappers or brittle scripting.
Reliable search and multi-format reading; OAuth auto-refreshes but testing apps expire tokens weekly; solid for 73/100 score but expect occasional MIME-type quirks.
Your agents need to organize Drive content across projects by searching and moving files/folders into structured hierarchies.
Fast search across entire Drive; moves to trash (not permanent delete); works great for automation but rate-limited by Google APIs.
Google Cloud Project + OAuth Setup
Required for API access; involves creating project, enabling 3+ APIs (Drive/Docs/Sheets), and desktop OAuth credentials—15-30min first-time cost.
OAuth Token Expiry in Testing
Google testing OAuth apps expire refresh tokens after 7 days; requires weekly re-auth or production OAuth verification.
Token Management
Tokens auto-save to ~/.config/google-drive-mcp/tokens.json (0600 perms); never commit to git; manual auth command if corrupted—use env var for custom paths.
Trust Breakdown
What It Actually Does
Lets your AI assistant search, read, and manage files directly in Google Drive without leaving your editor.[1][4] It handles automatic conversion of Google Docs, Sheets, and other workspace files into formats the AI can work with.[4]
Official Google Drive MCP server. Search, read, and manage files. Requires Google OAuth setup.
Fit Assessment
Best for
- ✓file-operations
- ✓knowledge-retrieval
- ✓data-analysis
Score Breakdown
Protocol Support
npx -y @modelcontextprotocol/server-gdriveCapabilities
Governance
- permission-scoping