Krakenfy Drive MCP
Enables AI agents to automate Google Drive tasks such as provisioning workspaces, reusing templates, inspecting folder structures, updating reports, and sharing files through user-controlled OAuth.
README
Krakenfy Drive MCP
Turn repeated Google Drive work into one instruction.
Krakenfy Drive MCP is an open-source server that lets AI agents provision workspaces, reuse company templates, inspect folder structures, update recurring reports, and deliver files through an OAuth project controlled by the user. It does not depend on native ChatGPT or Claude connectors.
Install it yourself · Deploy it with Krakenfy · Ask the community
Workflows it can automate
Client onboarding
Create the complete account workspace, build nested folders, and copy the correct Docs, Sheets, and Slides templates with consistent names in one tool call.
Recurring reporting
Find source material, read bounded spreadsheet ranges, append new records, update reporting cells, and place the finished deliverable in the correct folder.
Drive audits and delivery handoffs
Map a nested folder tree, identify misplaced work, organize approved files, and share the final folder with a person, group, or company domain after explicit confirmation.
Why companies use the managed service
The MCP is free and open source. You can install and adapt it yourself.
Krakenfy offers an optional implementation service for teams that want a production-ready workflow configured around their permissions, templates, operating process, and acceptance criteria. The service can include:
- Client-owned Google Cloud and OAuth configuration.
- Workflow mapping around one measurable recurring task.
- Safeguards and human approval points.
- Validation with real client files and exception handling.
- Private deployment, documentation, training, and operational handoff.
See the managed deployment options →
Capabilities
The server exposes 17 bounded MCP tools:
| Area | Available operations |
|---|---|
| Discovery | Search files, list folders, inspect metadata, and audit nested folder trees |
| Content | Read or export text and download files without overwriting local paths |
| Workspaces | Create folders and provision nested workspaces from Drive templates |
| Organization | Upload, copy, move, rename, and recoverably trash files |
| Delivery | Share files or folders with a user, group, or domain after confirmation |
| Sheets | Read validated bounded rectangles (max 10,000 cells per range), update ranges, and append rows |
| Drive support | Paginated results, shared-drive operations, and automatic backoff on rate limits |
Example
{
"name": "Acme",
"parentId": "customer-root-folder-id",
"folderPaths": [
"01 Intake",
"02 Work/Research",
"02 Work/Reports",
"03 Delivery"
],
"templates": [
{
"fileId": "report-template-id",
"name": "Acme — Weekly Report",
"targetFolderPath": "02 Work/Reports"
}
]
}
Pass this to drive_create_workspace and the agent creates the repeatable structure and template
copies. It can then use sheets_append_rows, drive_get_folder_tree, and drive_share_file to
continue the workflow.
Security model
- Credentials live outside the repository.
- Tokens are stored with
0600permissions. - Downloads never overwrite existing local files.
- Trash and sharing operations require
confirm: true. - Trash is recoverable through Google Drive.
- Text responses are limited to 2 MiB.
- Spreadsheet reads only accept bounded A1 rectangles, capped at 10,000 cells per range.
- Folder-tree reads have explicit depth and item limits.
- Rate-limited and transient Google API errors are retried with exponential backoff; non-idempotent writes are only retried when Google rejected the request before executing it.
- Every user supplies and controls their own Google Cloud project.
See SECURITY.md for vulnerability reporting and security details.
Installation
Follow the self-hosted installation guide to configure Google Cloud, authorize an account, and connect a compatible MCP client.
For private implementation, workflow adaptations, or a team rollout, see managed deployment.
Community and support
- Use Discussions for questions, workflow ideas, and examples.
- Use Issues for reproducible bugs and open-source feature requests.
- Use the Krakenfy assessment for private installation, workflow design, and commercial inquiries.
Development
npm ci
npm run check
npm test
License
MIT. See LICENSE.
This project is independent and is not endorsed by, sponsored by, or affiliated with Google. Google Drive is a trademark of Google LLC.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.