Skip to main content
Per-app Google setup is deprecated. All Google apps now share one Google OAuth client and one Redirect URI. To use your own client, follow the Google setup guide. Credentials saved for one Google app apply to all of them.

​
Overview

OneCLI connects AI agents to Google Drive through Google’s OAuth flow. Agents can search for files, read their contents, create new files, and organize them into folders. The gateway injects OAuth credentials into requests to the Google Drive API automatically. This is useful for agents that need to find documents, store outputs, or work with files shared across your team.

​
Connect on OneCLI Cloud (one click)

1

Go to Connections

Open the OneCLI dashboard and navigate to Connections > Google Drive.
2

Authorize

Click Connect Google Drive. You’ll go straight to Google: pick your account, review the permissions, and click Allow. No Google Cloud setup needed.
On self-hosted OneCLI, or to use your own Google client on Cloud, see Use your own Google client.

​
Use your own Google client

This is for self-hosted OneCLI, and for OneCLI Cloud when you choose Custom credentials instead of one-click. One Google client serves every Google app in OneCLI, so you set it up once. If you already did it for another Google app, skip to step 2.

1. Set up your Google client

Follow the Google setup guide. It enables the Google APIs, sets up the consent screen, creates the OAuth client, and adds the Redirect URI.You paste the client into Connections > Google Drive > Custom credentials, under the Redirect URI the guide asks you to register:
OneCLI Custom credentials card for Google Drive with the setup guide link, the Redirect URI and its copy button, and the Client ID and Client Secret fields.

Custom credentials for Google Drive in OneCLI.

Open Connections > Google Drive, select Connect Google Drive, pick your Google account, and click Allow.
OneCLI connect window for Google Drive showing Configuration required and the Configure credentials button.

The Google Drive connect window before a Google client is set up.

​
What agents can do

  • Search for files and folders by name, type, owner, or content
  • Read file metadata (name, size, sharing settings, last modified)
  • Download file contents, including Google Docs/Sheets/Slides exported to common formats
  • Upload new files to any folder
  • Create folders and organize files within them
  • Move, rename, and delete files
  • List files in a specific folder or shared drive
  • Manage file permissions (share, unshare, change access levels)
  • List and access shared drives

​
Controlling access

Access is per agent: grant the connection to each agent that needs it, choosing per tool what runs freely, what needs human approval, and what stays blocked — a read-only agent is a single grant. Organization rules add guardrails on top, like rate limits and blanket blocks. Everything is checked before credential injection, so a blocked request never reaches Google Drive.