handoff-mcp
Enables AI assistants to manage complex development workflows by creating structured handoffs between strategic planning and tactical implementation, with project management, task tracking, and intelligent scaffolding.
README
Handoff MCP Server
Strategic-to-tactical workflow orchestration for AI-assisted development. Bridge the gap between high-level planning and hands-on implementation.
Overview
Handoff MCP is a Model Context Protocol server that helps AI assistants manage complex development workflows by creating clear handoffs between strategic planning and tactical implementation. It provides project management, task tracking, and intelligent scaffolding capabilities.
Key Features
- 🏗️ Project Management - Organize work into projects with tags and metadata
- 📋 Handoff System - Create structured handoffs from strategy to implementation
- 🚀 Smart Scaffolding - Generate project structures from templates
- 💾 Local Storage - SQLite database for fast, offline-first operation
- 🤖 NLP Analysis - Intelligent requirement parsing and classification
- 📊 Analytics - Track project progress and success metrics
Installation
Via npm (recommended)
npm install -g handoff-mcp
From source
git clone https://github.com/coladapo/handoff-mcp.git
cd handoff-mcp
npm install
npm run build
Configuration
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"handoff": {
"command": "npx",
"args": ["handoff-mcp"]
}
}
}
For local development:
{
"mcpServers": {
"handoff": {
"command": "node",
"args": ["/absolute/path/to/handoff-mcp/dist/index.js"]
}
}
}
Usage Examples
Creating a Project
// Using the MCP tool in Claude
await use_tool('create_project', {
name: 'E-commerce Platform',
description: 'Modern e-commerce site with React and Node.js',
tags: ['web', 'fullstack', 'production'],
default_project_info: {
language: 'TypeScript',
framework: 'React + Express',
build_command: 'npm run build',
test_command: 'npm test'
}
});
Creating a Handoff
await use_tool('create_handoff', {
project_id: 'proj_123',
title: 'Implement user authentication',
strategic_context: 'Need secure user authentication for the platform with JWT tokens and OAuth support',
tactical_requirements: [
'Create login/signup endpoints',
'Implement JWT token generation',
'Add OAuth2 providers (Google, GitHub)',
'Create middleware for route protection'
],
acceptance_criteria: [
'Users can register with email/password',
'JWT tokens expire after 24 hours',
'OAuth login works with Google',
'Protected routes return 401 when unauthorized'
],
priority: 'high'
});
Generating Scaffolding
await use_tool('generate_scaffold', {
template_name: 'express',
project_name: 'auth-service',
target_path: './services/auth',
variables: {
port: 3001,
database: 'PostgreSQL',
authentication: true
}
});
Available Tools
Project Management
| Tool | Description |
|---|---|
create_project |
Create a new project with metadata |
list_projects |
List all projects with filtering |
get_project |
Get detailed project information |
archive_project |
Archive completed projects |
get_project_stats |
Get project analytics and metrics |
Handoff Management
| Tool | Description |
|---|---|
create_handoff |
Create a strategic-to-tactical handoff |
get_handoff |
Retrieve handoff details |
list_handoffs |
List handoffs with filtering |
update_handoff_status |
Update handoff progress |
add_handoff_note |
Add notes to a handoff |
verify_handoff |
Verify completion criteria |
generate_implementation_brief |
Generate detailed implementation plan |
Scaffolding
| Tool | Description |
|---|---|
list_templates |
List available project templates |
preview_scaffold |
Preview files before generation |
generate_scaffold |
Generate project structure |
analyze_requirements |
NLP analysis of requirements |
Project Templates
Handoff MCP includes several built-in templates:
- express - Node.js Express API server
- fastapi - Python FastAPI backend
- react - React frontend application
- mcp-server - MCP server boilerplate
Data Storage
Data is stored locally in SQLite:
- Location:
~/.puo-memo/cursor_handoffs.db - Backup: Automatic daily backups
- Privacy: All data stays on your machine
Architecture
handoff-mcp/
├── src/
│ ├── index.ts # MCP server entry point
│ ├── storage.ts # SQLite database layer
│ ├── types.ts # TypeScript interfaces
│ └── scaffolding/ # Template engine
│ └── ScaffoldingEngine.ts
├── templates/ # Project templates
│ ├── express/
│ ├── fastapi/
│ ├── react/
│ └── mcp-server/
└── tests/ # Test suite
Development
Prerequisites
- Node.js 18+
- npm or yarn
- TypeScript 5.5+
Setup
# Clone repository
git clone https://github.com/coladapo/handoff-mcp.git
cd handoff-mcp
# Install dependencies
npm install
# Build
npm run build
# Run tests
npm test
# Development mode
npm run dev
Testing
# Run all tests
npm test
# Run specific test suite
npm run test:storage
npm run test:scaffolding
# Test coverage
npm run test:coverage
Contributing
We welcome contributions! Please see CONTRIBUTING.md for guidelines.
Areas for Contribution
- Additional project templates
- Enhanced NLP capabilities
- Cloud storage adapters
- Integration with more AI assistants
- Improved analytics and reporting
Roadmap
- [ ] Cloud sync support (Supabase/PostgreSQL)
- [ ] Team collaboration features
- [ ] Web dashboard for project overview
- [ ] GitHub integration
- [ ] Custom template creation UI
- [ ] Real-time progress tracking
- [ ] Export/import functionality
Support
- Issues: GitHub Issues
- Discussions: GitHub Discussions
- Documentation: Wiki
License
MIT License - see LICENSE file for details.
Acknowledgments
Built with the Model Context Protocol SDK by Anthropic.
Made with ❤️ for the AI-assisted development community
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。