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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。