About Google Drive
Google Drive is an MCP server for managing Drive files, folders, comments, and permissions. Its OAuth proxy forwards authorization to Google without retaining tokens or state.
Key features
- 01Search and list files
- 02Download, upload, and update files
- 03Create and organize folders
- 04Manage comments and replies
- 05View and change file permissions
Use cases
- 01Find and read information in Drive files
- 02Create folder structures for a project
- 03Review comments across presentation files
- 04Translate and review a document collection
MCP support
Exposes Google Drive file, folder, comment, and permission operations as tools for MCP clients. It proxies OAuth and uses bearer tokens for Drive API requests.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y google-drive-mcpGOOGLE_ACCESS_TOKENSecretGoogle OAuth access token with Drive scopes.MCP_TRANSPORTTransport type.GOOGLE_CLIENT_IDGoogle OAuth client ID.GOOGLE_CLIENT_SECRETSecretGoogle OAuth client secret.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEgoogle-drive-mcp
MCP server for Google Drive - list, search, upload, download, and manage files and folders.
Use Cases
Answer from files: "What was our revenue target in the Q2 board deck?" → searches Drive, reads the relevant doc, and answers your question.
Project scaffolding: Starting a new vendor onboarding → creates a folder structure with subfolders for contracts, compliance, deliverables, and meeting notes, plus template docs and sheets.
Feedback synthesis: "Summarize the feedback from my manager across my last 10 presentation decks" → reads comments from multiple files and identifies themes and development areas.
Localization workflow: "We're onboarding contractors in Japan - translate the onboarding folder from English to Japanese and flag anything that needs local adaptation (HR policies, holidays, etc.)" → reads multiple docs, translates, and highlights areas needing review.
(These are just examples - any workflow that needs file search, reading, or organization can use this. Use in combination with google-docs-mcp for reading/editing Google Docs, or google-sheets-mcp for Google Sheets.)
Setup
1. Create Google OAuth credentials
- Go to Google Cloud Console
- Create a new project (or use existing)
- Enable the Google Drive API
- Go to APIs & Services → OAuth consent screen, set up consent screen
- Go to APIs & Services → Credentials → Create Credentials → OAuth client ID
- Choose Web application
- Add
http://localhost:3000/callbackto Authorized redirect URIs - Note your Client ID and Client Secret
2. Run the server
GOOGLE_CLIENT_ID='your-client-id' \
GOOGLE_CLIENT_SECRET='your-client-secret' \
MCP_TRANSPORT=http \
npm start
The server runs on http://localhost:3000 by default. Change with PORT=3001.
3. Add to your MCP client
With the server running, follow the instructions on install-mcp, which generates the right config for your MCP client (Claude Code, Claude Desktop, Cursor, Cline, VS Code, and more).
Architecture
This server acts as an OAuth proxy to Google:
graph LR
A[MCP client] <--> B[google-drive-mcp] <--> C[Google OAuth/API]
- Server advertises itself as an OAuth authorization server via
/.well-known/oauth-authorization-server /registerreturns the Google OAuth client credentials/authorizeredirects to Google, encoding the client's callback URL in state/callbackreceives the code from Google and forwards to the client's callback/tokenproxies token requests to Google, injecting client credentials/mcphandles MCP requests, using the bearer token to call Drive API
The server holds no tokens or state - it just proxies OAuth to Google.
Tools
| Tool | Description |
|---|---|
| Files | |
files_list | List/search files using Drive query syntax |
file_get | Get file metadata |
file_download | Download file content (supports export for Google Docs/Sheets) |
file_upload | Upload a new file |
file_update | Update file content or metadata |
file_copy | Copy a file |
file_move | Move a file to a different folder |
file_trash | Move to trash |
file_untrash | Restore from trash |
file_delete | Permanently delete |
| Folders | |
folder_create | Create a new folder |
| Comments | |
comments_list | List comments on a file |
comment_get | Get a comment and its replies |
comment_create | Add a comment to a file |
comment_reply | Reply to a comment |
comment_resolve | Resolve or unresolve a comment |
| Replies | |
replies_list | List replies to a comment |
reply_get | Get a specific reply |
reply_update | Update a reply |
reply_delete | Delete a reply |
| Permissions | |
permissions_list | List who has access to a file |
permission_get | Get a specific permission |
permission_create | Share a file with a user, group, domain, or anyone |
permission_update | Change a user's access level |
permission_delete | Revoke access to a file |
Drive Query Syntax
The files_list tool supports Drive's query syntax for filtering:
# By name
name contains 'report'
name = 'Budget 2024'
# By type
mimeType = 'application/pdf'
mimeType = 'application/vnd.google-apps.folder'
mimeType = 'application/vnd.google-apps.document'
# By folder
'folder-id' in parents
# By ownership
'[email protected]' in owners
# Combined
name contains 'report' and mimeType = 'application/pdf'
Google Drive API Scopes
drive- Full access to Drive files
Contributing
Pull requests are welcomed on GitHub! To get started:
- Install Git and Node.js
- Clone the repository
- Install dependencies with
npm install - Run
npm run testto run tests - Build with
npm run build
Releases
Versions follow the semantic versioning spec.
To release:
- Use
npm version <major | minor | patch>to bump the version - Run
git push --follow-tagsto push with tags - Wait for GitHub Actions to publish to the NPM registry.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.