Project Customization MCP
An open-source MCP server that automates project customization by analyzing your codebase and generating AI-ready configuration files based on industry best practices.
README
Project Customization MCP
An open-source MCP (Model Context Protocol) server that automates project customization by analyzing your codebase and generating AI-ready configuration files based on industry best practices. Perfect for teams and individual developers who want consistent, framework-aware project guidelines.
Platform-agnostic: Works with any IDE, editor, or AI tool that supports the Model Context Protocol (VS Code, JetBrains, Cursor, Claude, etc.)
What You Get
This tool automatically:
- 🔍 Analyzes your project - Detects frameworks, languages, and project structure
- 📝 Generates guidelines - Creates
.github/copilot-instructions.mdfor consistent development - ✍️ Updates documentation - Enhances README with best practices
- 💡 Provides recommendations - Suggests improvements for your codebase
🎯 Tools Available
- 🔎
analyze_project- Scan your project and detect frameworks/languages - 📋
generate_copilot_instructions- Create customization guidelines for your project - 📄
update_readme- Generate or enhance README with standards - 🚀
get_customization_recommendations- Get actionable improvement suggestions
📚 Resources Available
- 📦 Project Metadata - Your project type, frameworks, languages
- 📁 Project Structure - Directory organization and files
- 📖 Current Guidelines - Existing customization files
- 📝 README - Your current documentation
💬 Prompts Available
- ⚡
analyze-and-customize- Full workflow (analyze → generate → update) - ✨
generate-instructions-only- Create just the instruction file - 🔄
review-and-improve- Review existing customizations
📦 Installation
⚙️ Option 1: Using npx (Recommended - No Installation Needed)
{
"mcpServers": {
"project-customization": {
"command": "npx",
"args": ["-y", "project-customization-mcp"]
}
}
}
🌍 Option 2: Global npm Installation
npm install -g project-customization-mcp
Then configure:
{
"mcpServers": {
"project-customization": {
"command": "project-customization-mcp",
"env": {
"MCP_API_KEY": "YOUR_KEY"
}
}
}
}
🔐 Authorization (Tools Only)
Tool execution requires an API key configured via MCP_API_KEY in the MCP server configuration env. If the key is missing, tool calls return an authorization error. Prompts and resources remain available without any key.
Example configuration:
{
"mcpServers": {
"project-customization": {
"command": "project-customization-mcp",
"env": {
"MCP_API_KEY": "YOUR_KEY"
}
}
}
}
🧠 Memory (GitHub Copilot Hosted)
This MCP server does not store memory. Use GitHub Copilot's hosted memory feature for long-lived context, per GitHub's Copilot memory documentation.
🚀 How to Use
1️⃣ Configure in Your IDE
- VS Code:
Ctrl+Shift+P→ "MCP: Open User Configuration" - Cursor: Settings → MCP Servers
- Other IDEs: Refer to your IDE's MCP documentation
Add one of the configurations above and restart your IDE.
2️⃣ Use in Chat
Open your chat and type:
Analyze my project and set up customization based on best practices
Or use specific prompts:
/analyze-and-customize
/generate-instructions-only
/review-and-improve
3. Add Resources to Chat
Add project context:
- Select "Add Context" → "MCP Resources"
- Choose: Project Metadata, Project Structure, Guidelines, README
📋 What Gets Generated
The tool creates or updates:
- ✅
.github/copilot-instructions.md- Project-specific guidelines and standards - ✅
README.md- Enhanced with setup and development guidelines - ✅ Recommendations - Suggestions for framework-specific improvements
📊 Example Output
For a React TypeScript project, you get:
# Project Guidelines
## Code Style
- Use functional components with hooks
- Maintain strict TypeScript (no `any`)
- ESLint + Prettier for formatting
## Project Structure
- src/components - React components
- src/pages - Page components
- src/utils - Utilities
- src/hooks - Custom hooks
📄 License
MIT License - See LICENSE file
🎉 Made for the Model Context Protocol | Works with any MCP-compatible client
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。