Home / Integrations / Google Drive
Integration

Connect your AI to Google Drive

UniversalBench lets your AI find and fetch Google Drive files through one connection, using a Google access token you provide, then pull a file straight in to process. It works with Claude, ChatGPT, Gemini, and any other MCP-compatible AI through one connection.

Connect Google Drive in three steps

Get a Google access token

Create an OAuth access token that includes the Google Drive scope.

Save it once in the secret vault

Store the token in your UniversalBench secret vault, for example as GOOGLE_TOKEN.

Connect and ask

Your AI calls the Drive API and references your token as a placeholder in the Authorization header, substituted at call time. It lists and fetches files and pulls one straight into the sandbox to process.

# add this one URL to Claude, ChatGPT, or Gemini https://universalbench-mcp.penantiaglobal.workers.dev/u/<your-key> # save your Google access token once GOOGLE_TOKEN = ya29.your_access_token # used in the header as a placeholder Authorization: Bearer {{GOOGLE_TOKEN}}
UniversalBench dashboard secret vault: enter the secret name on the left such as GITHUB_TOKEN, paste the secret value on the right, then save
The secret vault in your UniversalBench dashboard. Enter the secret name on the left, paste the secret value on the right, then Save. The matching capability unlocks automatically.

What your AI can do

Is there a Google Drive MCP server to install?

No separate server to install or host. UniversalBench is the MCP server, and Google Drive is one of the things it does for your AI behind a single connection. Save your credential once in the encrypted secret vault under GOOGLE_TOKEN and it is used automatically after that.

The same connection also handles finding and processing Drive files from your AI and more, so one setup covers far more than Google Drive alone.

Frequently asked questions

How do I connect my AI to Google Drive?

First, create an OAuth access token that includes the Google Drive scope. Then save it in your UniversalBench secret vault under the name GOOGLE_TOKEN, which unlocks the capability automatically. Finally, add the one MCP URL to your AI and ask in plain language.

Where do I put the credential?

In your UniversalBench secret vault, under the name GOOGLE_TOKEN. It is encrypted, used automatically by the matching capability, and never shown back to you or sent to the model in plain text.

Does this work with ChatGPT and Gemini?

Yes. UniversalBench connects through one standard MCP link, so it works with Claude, ChatGPT, Gemini, and any MCP-compatible AI. You paste one URL and the capability is there.

More integrations

Connect your AI to Google Drive free

One URL, first 1,000 calls free, no credit card.

Get your API key →