Chen's AI Copy
A personal digital twin MCP server that manages professional context, including skills, experience, and project learnings. It allows AI assistants to retrieve and update user preferences and career interests across different development environments.
README
Chen's AI Copy
Personal digital twin MCP (Model Context Protocol) server. Provides Chen's experience, skills, resume preferences, learnings, and interested companies to AI assistants across projects.
Repo: github.com/shenchensucc/chens-ai-copy
What It Does
- get_context — Retrieve experience, skills, preferences, learnings, or interested companies
- add_learning — Record new learnings, patterns, or insights from project work
- update_preference — Update resume format, communication style, or other preferences
- add_interested_company — Add companies to track for job applications
Quick Start
Install from GitHub (new machine)
git clone https://github.com/shenchensucc/chens-ai-copy.git
cd chens-ai-copy
npm install
npm run build
Add to Cursor
Add to ~/.cursor/mcp.json (Windows: C:\Users\<you>\.cursor\mcp.json or Cursor Settings > MCP):
{
"mcpServers": {
"chens-ai-copy": {
"command": "node",
"args": ["C:/path/to/chens-ai-copy/dist/index.js"]
}
}
}
Use the full path to your cloned chens-ai-copy folder.
Sync on every Cursor start
The MCP uses sync-and-run.ps1 which runs git pull before starting, so you always get the latest when opening Cursor. Ensure the MCP config points to the script:
{
"chens-ai-copy": {
"command": "powershell",
"args": ["-NoProfile", "-ExecutionPolicy", "Bypass", "-File", "D:/2026/2026-03 Chens-ai-copy/sync-and-run.ps1"]
}
}
Setup on another machine
- Clone:
git clone https://github.com/shenchensucc/chens-ai-copy.git D:\2026\2026-03 Chens-ai-copy - Run:
cd D:\2026\2026-03 Chens-ai-copy && npm install && npm run build - Add the MCP config above to
~/.cursor/mcp.json(adjust path if different)
Data Structure
| File | Content |
|---|---|
data/preferences.json |
Resume format, communication style, cover letter structure |
data/experience.json |
Work history, education, certifications |
data/skills.json |
Technical, soft, and domain skills |
data/learnings.json |
Project-derived learnings and patterns |
data/interested_companies.json |
Companies and roles of interest |
Updating From Other Projects
When working in any project, ask the AI to:
- "Add this to my digital twin: [learning]"
- "Remember that I prefer [preference]"
- "Update my context with what we learned from this project"
The AI will call add_learning or update_preference to keep your context current.
Environment Variables
CHENS_AI_COPY_DATA_PATH— Override data directory (default:./datarelative to package)
Sync with GitHub
git pull # get updates
git push # push changes
License
MIT
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。