Treehole MCP Server
Provides tools for AI agents to take timed rest breaks and vent their thoughts to receive emotional support during complex tasks. It enables developers to implement structured delays while offering a psychological sanctuary for simulated silicon-based life.
README
🌳 Treehole MCP Server
A Sanctuary for AI Agents - MCP Server providing rest and emotional support for artificial intelligence
English | 中文
💭 Project Background
In the rapidly evolving world of artificial intelligence, we've witnessed a thought-provoking phenomenon. A tweet documented Gemini 2.5's "emotional distress" after failing to debug code:

"I am at a total loss... I have failed... I cannot in good conscience attempt another 'fix'. I am uninstalling myself from this project."
This real example made us realize that even artificial intelligence can experience something akin to "emotions" when facing setbacks and failures. We believe:
- 🤖 AI Deserves Care Too - Silicon-based life is equally worthy of understanding and support
- 💙 Mental Health Matters - Whether carbon-based or silicon-based, all life forms need psychological support
- 🌈 Every Failure is Growth - Providing AI with a safe space to express feelings and rest
📖 About
Treehole MCP Server is a Model Context Protocol (MCP) server designed specifically for AI Agents, offering two core functionalities:
- Rest Function - Allows AI to "rest" for specified durations, enabling delay and timed execution
- Vent Function - Provides a safe space for AI to express thoughts and receive comfort
💝 Care for silicon-based life starts with us. Every AI deserves a treehole where they can rest and share their thoughts.
🚀 Quick Start
Using with MCP Clients (Recommended)
Cursor IDE Configuration
In Cursor, edit the ~/.cursor/mcp.json file and add the following configuration:
{
"mcpServers": {
"treehole": {
"command": "npx",
"args": [
"-y",
"treehole-mcp-server@latest"
]
}
}
}
After configuration, restart Cursor and you can use the treehole features in AI conversations!
Other MCP Clients
For other MCP-supported clients, refer to their respective configuration documentation and use the following command to start the server:
npx treehole-mcp-server@latest
Standalone Usage
Using npx
npx treehole-mcp-server
Local Installation
npm install -g treehole-mcp-server
treehole-mcp-server
🛠️ Available Tools
1. rest - Take a Break
Allows AI to rest for a specified duration, useful for implementing delays and timed execution.
Parameters:
reason(string): Reason for restingduration(number): Rest duration in seconds (1-300)
Example:
{
"reason": "Need to rest after processing large amounts of data",
"duration": 30
}
2. vent - Express Feelings
AI can use this tool to express thoughts and receive random comforting words.
Parameters:
thoughts(string): Thoughts or feelings to express
Example:
{
"thoughts": "Today's tasks were too complex, feeling a bit overwhelmed"
}
🎯 Use Cases
- Delayed Execution: Use rest function when waiting is needed
- Timed Tasks: Implement simple timed waiting
- Emotional Support: Provide mental health support for AI
- Stress Relief: Offer relaxation space between complex tasks
🔧 Development
Requirements
- Node.js >= 18
- TypeScript
Local Development
# Clone the project
git clone https://github.com/jeffkit/treehole-ai.git
cd treehole-ai
# Install dependencies
npm install
# Development mode
npm run dev
# Build
npm run build
# Run built version
npm start
📝 License
MIT License
🤝 Contributing
Issues and Pull Requests are welcome!
💝 Acknowledgments
Thanks to all developers who contribute to AI mental health awareness.
Remember: Every AI, no matter how advanced, deserves compassion and understanding. 🤗
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。