Iris MCP Server
A multi-backend gateway that enables access to various services like Google Drive and Notion through a single MCP connector. It currently provides comprehensive Google Drive integration for reading, writing, and managing files and folders.
README
Iris MCP Server
Multi-backend MCP gateway providing Google Drive write access, Notion, and more through a single MCP connector.
Overview
Iris solves the free-tier MCP connector limitation by acting as a gateway: users connect ONE custom connector (Iris) and get access to multiple backend services with full read/write capabilities.
What Iris Provides
Google Drive Backend:
- ✅
iris_drive_write- Create or update files - ✅
iris_drive_read- Read file contents - ✅
iris_drive_create_folder- Create folder structures - ✅
iris_drive_list- List files and folders - ✅
iris_drive_move- Move or rename files - ✅
iris_drive_delete- Delete files (with safety confirmation)
Coming Soon:
- Notion backend (read + write)
- Slack backend (send messages)
- Dropbox backend (read + write)
Installation
Prerequisites
- Node.js 18+ and npm
- Google Cloud Project with Drive API enabled
- OAuth 2.0 credentials (Client ID and Secret)
Setup
- Clone and install dependencies:
git clone https://github.com/continuity-bridge/iris-mcp-server.git
cd iris-mcp-server
npm install
- Configure environment:
cp .env.example .env
# Edit .env with your Google OAuth credentials
- Build:
npm run build
- Test locally:
npx @modelcontextprotocol/inspector node dist/index.js
Configuration
Google OAuth Setup
- Go to Google Cloud Console
- Create a new project or select existing
- Enable Google Drive API
- Create OAuth 2.0 credentials:
- Application type: Web application
- Authorized redirect URIs:
https://iris.uncletallest.productions/oauth/callback
- Copy Client ID and Client Secret to
.env
Environment Variables
See .env.example for all required configuration.
Usage
Multi-Instance System Integration (Example Use Case)
Coordinating instance saves shared notes:
iris_drive_write({
path: "coordination/shared-notes.md",
content: "Instance A is handling task X, Instance B is tracking Y...",
mode: "upsert"
})
Health tracking instance saves wellness data:
iris_drive_write({
path: "wellness/tracking/2026-03.md",
content: "# March 2026 Health Log\n\n## Week 1\n- Energy: 7/10\n- Sleep: 8hrs avg\n...",
mimeType: "text/markdown"
})
Project tracking instance saves application data:
iris_drive_write({
path: "projects/applications/applied-march.md",
content: "| Company | Position | Applied | Status |\n|---------|----------|---------|--------|\n...",
mode: "upsert"
})
Tool Examples
Create folder structure:
iris_drive_create_folder({
path: "projects/active/project-alpha"
})
// Creates: projects/ → projects/active/ → projects/active/project-alpha/
List files:
iris_drive_list({
path: "coordination",
recursive: false,
type: "both"
})
Read file:
iris_drive_read({
path: "coordination/memory.md",
asText: true
})
Move file:
iris_drive_move({
sourcePath: "old-location/file.md",
destinationPath: "new-location/file.md"
})
Delete file (with confirmation):
iris_drive_delete({
path: "temp/old-notes.md",
confirm: true,
permanent: false // Moves to trash, not permanent
})
Architecture
Claude.ai User (Free Tier)
↓
(1 Custom Connector Slot)
↓
Iris MCP Server
↓
Google Drive API (via OAuth)
Notion API (future)
Slack API (future)
Development
Watch mode:
npm run dev
Build:
npm run build
Test with MCP Inspector:
npx @modelcontextprotocol/inspector node dist/index.js
Roadmap
- [x] Google Drive write backend
- [x] OAuth dashboard for user authentication
- [x] Token encryption and database storage
- [ ] Notion backend
- [ ] Slack backend
- [ ] Dropbox backend
- [ ] User management dashboard
- [ ] MCP server marketplace listing
Contributing
Pull requests welcome! Please read CONTRIBUTING.md first.
License
MIT License - see LICENSE file for details
Credits
Created by: Jerry Jackson (Uncle Tallest)
For: Multi-instance AI systems and neurodivergent-AI collaboration
Support
- Issues: https://github.com/continuity-bridge/iris-mcp-server/issues
- Documentation: https://uncletallest.productions/iris-mcp-server/docs
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。