Taiwan Holiday
About
Provides Taiwan national holidays and compensatory workday information. Data is fetched and cached automatically.
Details
- Author
- lis186
- Categories
- Productivity, Other
Jump to
Setup
Install Taiwan Holiday in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/lis186/taiwan-holiday-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
Provides Taiwan national holidays and compensatory workday information. Data is fetched and cached automatically.
一個基於 Model Context Protocol (MCP) 的台灣假期查詢伺服器,提供準確的台灣國定假日和補班日資訊。
npm install -g taiwan-holiday-mcp taiwan-holiday-mcp
git clone https://github.com/lis186/taiwan-holiday-mcp.git cd taiwan-holiday-mcp npm install npm run build npm start
{ "mcpServers": { "taiwan-holiday": { "command": "npx", "args": ["taiwan-holiday-mcp"] } } }
- macOS:~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:%APPDATA%\Claude\claude_desktop_config.json
{ "mcp": { "servers": { "taiwan-holiday": { "command": "npx", "args": ["taiwan-holiday-mcp"] } } } }
安裝完成後,你可以直接在 Claude Desktop 中用自然語言與 AI 對話,詢問台灣假期相關問題:
- ✅ 2025年10月10日是國慶日,是假期
- 📅 2025年1月共有14個假期,包含春節連假
- 📊 2025年總共有115個假期
你:"我想規劃2025年第一季的旅遊,幫我找出有哪些連假可以安排?"
- 春節連假:1月27日-31日(5天)
- 228連假:2月28日-3月2日(3天)
- 其他週末假期安排建議
- date(string): 日期,格式為YYYY-MM-DD或YYYYMMDD
{ "success": true, "data": { "date": "2025-10-10", "isHoliday": true, "description": "國慶日", "week": "五", "normalizedDate": "20251010" } }
- start_date(string): 開始日期
- end_date(string): 結束日期
{ "success": true, "data": { "startDate": "2025-01-01", "endDate": "2025-01-31", "holidays": [...], "totalCount": 14, "summary": "在 2025-01-01 到 2025-01-31 期間共有 14 個假期" } }
- year(number): 年份,2017 年起(實際可查年份由上游資料決定)
- month(number, 可選): 月份 (1-12)
{ "success": true, "data": { "year": 2025, "statistics": { "year": 2025, "totalHolidays": 115, "nationalHolidays": 113, "compensatoryDays": 2, "holidayTypes": {...} }, "summary": "2025 年共有 115 個假期" } }
- taiwan-holidays://years- 支援的年份列表
- taiwan-holidays://holidays/{year}- 指定年份的完整假期資料
- taiwan-holidays://stats/{year}- 指定年份的統計資訊
問題:Claude Desktop 顯示 "無法連接到 MCP 伺服器"
# 檢查 Node.js 版本(需要 18+) node --version # 重新安裝套件 npm uninstall -g taiwan-holiday-mcp npm install -g taiwan-holiday-mcp # 測試伺服器 taiwan-holiday-mcp --version
- 確保使用正確格式:YYYY-MM-DD或YYYYMMDD
- 檢查日期是否有效(例如:2025-02-30 是無效日期)
# 檢查網路連接 curl -I https://cdn.jsdelivr.net/gh/ruyut/TaiwanCalendar/data/2025.json # 清除快取(如果有問題) rm -rf ~/.taiwan-holiday-mcp-cache
# 複製專案 git clone https://github.com/lis186/taiwan-holiday-mcp.git cd taiwan-holiday-mcp # 安裝依賴 npm install # 執行測試 npm test # 建置專案 npm run build # 啟動開發模式 npm run dev
- SmartCache: 98.97% ✅
- HealthMonitor: 98.78% ✅
- DateParser: 97.77% ✅
- CircuitBreaker: 100% ✅
- GracefulShutdown: 88.34% ✅
- 首次 API 呼叫:< 2 秒
- 快取 API 呼叫:< 100ms
- 併發處理:支援 10+ 併發請求
- 記憶體使用:< 50MB
- 測試穩定性:100% 通過率,企業級品質標準
- 程式碼覆蓋率:92.34%(遠超業界 80% 標準)
- Fork 專案
- 建立功能分支 (git checkout -b feature/amazing-feature)
- 提交變更 (git commit -m 'Add amazing feature')
- 推送到分支 (git push origin feature/amazing-feature)
- 開啟 Pull Request
- 本服務依賴外部資料來源,可能因網路問題或資料來源異常而暫時無法使用
- 我們不保證服務的 100% 可用性或回應時間
- 建議在關鍵應用中實作適當的錯誤處理和備援機制
在法律允許的最大範圍內,本專案的作者和貢獻者不對因使用本軟體而產生的任何直接、間接、偶然、特殊或後果性損害承擔責任。
- taiwan-holiday-cli—— 同一資料來源的命令列工具,適合終端機與腳本使用
- taiwan-holiday-skills—— 打包好的 Claude Agent Skill(底層透過 CLI 呼叫)
- TaiwanCalendar- 提供準確的台灣假期資料
- Model Context Protocol- 提供標準化的 AI 工具協議
支援年份: 2017 年起,上限跟隨上游資料(新年度發布即自動支援)
MCP SDK: @modelcontextprotocol/sdk ^1.13.0
Node.js 需求: ≥ 18.0.0
品質狀態: 企業級生產就緒 ✅
Chinese calendar MCP server — holidays, lunar/solar conversion, 24 solar terms, workday calculation, 13 endpoints, zero API dependency
High-precision temporal calculation engine supporting ISO 8601 parsing, timezone conversions, business days, duration math, relative time formatting, and full calendar generation.
Connect AI clients to Cal.com scheduling through the Model Context Protocol using the hosted server at mcp.cal.com or a local instance.
Sync Calendars, Scheduling Links, AI Executive Scheduling Assistant, Unified Calendar
Automated document processing and extraction
Great Question is an Agentic UX research platform for product builders. Its MCP lets AI agents create studies directly from any AI tool, surface insights, find the right research candidates, and query your entire research repository.
MCP server to interact with Routine: calendars, tasks, notes, etc.
Query contacts, companies, and relationship data extracted from your email and calendar. Build pre-meeting reports, find warm intros, and identify fading relationships.
Create and edit Tally forms and analyze submissions
An MCP server for ActivityWatch, allowing interaction with your personal time tracking data.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.




