Connect
Optimize
Secure
Announcing StackOne Defender: leading open-source prompt injection guard for your agent • Read More →
Production-ready Google Drive MCP server with 47 extensible actions — plus built-in authentication, security, and optimized execution.
Coverage
Create, read, update, and delete across Google Drive — and extend your agent's capabilities with custom actions.
Authentication
Per-user OAuth in one call. Your Google Drive MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →Security
Every Google Drive tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →Performance
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Google Drive call.
Tools Discovery →A Google Drive MCP server lets AI agents read and write Google Drive data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Google Drive MCP server ships with 47 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
Every action from Google Drive's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
List unified files in Google Drive with StackOne unified filters
Get a unified file by ID with metadata mapped to StackOne unified schema
Downloads unified file content from Google Drive
List unified folders in Google Drive with StackOne unified filters
Get a unified folder by ID with metadata mapped to StackOne unified schema
List unified shared drives in Google Drive
Get a unified shared drive by ID with metadata mapped to StackOne unified schema
Creates a copy of a file and applies any requested updates with patch semantics
Creates a new file or folder with metadata only
List files, folders, and other Drive items. Returns raw Google Drive API response
Get file, folder, or Drive item by ID
Updates a file's metadata using patch semantics
Permanently deletes a file without moving it to the trash
Creates a new shared drive
Lists the user's shared drives (formerly Team Drives)
Gets a shared drive's metadata by ID
Updates the metadata for a shared drive
Permanently deletes a shared drive for which the user is an organizer
Creates a new permission for a file or shared drive
Lists a file's or shared drive's permissions
Gets a permission by ID
Updates a permission with patch semantics (modify role, expiration time, etc.)
Deletes a permission (revokes access)
Creates a new comment on a file
Lists a file's comments
Gets a comment by ID
Updates a comment with patch semantics (edit content or resolve/reopen)
Deletes a comment
Creates a reply to a comment
Gets a reply by ID
Updates a reply with patch semantics
Deletes a reply
Lists a file's revisions
Gets a revision's metadata or content by ID
Updates a revision with patch semantics
Permanently deletes a file version
Returns a paginated list of access proposals.
Retrieves an access proposal by ID
Lists a comment's replies
Gets the starting pageToken for listing future changes
Returns a paginated list of changes.
Gets information about the user, the user's Drive, and system capabilities
Permanently deletes all of the user's trashed files
Generates a set of file IDs which can be provided in create or copy requests
Hides a shared drive from the default view
Restores a shared drive to the default view
Approves or denies an access proposal
One endpoint. Any framework. Your agent is talking to Google Drive in under 10 lines of code.
MCP Clients
Agent Frameworks
{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}83+ actions
82+ actions
46+ actions
19+ actions
2+ actions
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
origin_owner_id.All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.