Nager.Date MCP Server

Nager.Date MCP Server

Provides public holidays, long weekends, and country data for 202 countries via the Nager.Date API, with client-side filtering and timezone-aware checks.

Category
访问服务器

README

Nager.Date MCP Server

MCP server wrapping the Nager.Date API — public holidays for 202 countries with local names, types, long weekends, and regional subdivisions.

Tools

  • get_holidays(country, year?, type?, county?) — All holidays for a country/year. Filter by type (Public, Bank, School, Observance, etc.) or subdivision (e.g. GB-SCT, DE-BY). Includes day-of-week.
  • get_next_holidays(country, county?) — Upcoming holidays from today forward.
  • get_long_weekends(country, year?) — Long weekends with bridge day suggestions.
  • is_today_holiday(country, county?, offset?) — Quick yes/no: is today a public holiday? Optional UTC offset for timezone.
  • list_countries(query?) — All 202 supported countries; optional case-insensitive substring filter on name/code.
  • get_country_info(country) — Country metadata: official name, region, borders.
  • get_worldwide_holidays() — Every holiday happening today, globally.

Return shape convention

get_holidays and get_next_holidays normally return a plain list of holiday objects. When a filter produces a result that could mislead, they instead return a dict {"holidays": [...], "note": "..."} where note explains the caveat:

  • A type filter matched no holiday (the country may use a different type label).
  • A county filter matched no regional holiday, so only national/global holidays are shown (often a typo'd subdivision code).

LLM consumers should handle both shapes: if the result is a dict, surface the note and read the holidays from result["holidays"]; if it's a list, use it directly. Error and no-data cases return a plain string message.

Features

  • No API key required — uses the free public API
  • In-memory TTL cache (24h for static data, 1h for "next" endpoints, 7d for country info)
  • Country code normalization (lowercase accepted)
  • Day-of-week enrichment on all holiday results
  • Client-side filtering by holiday type and subdivision
  • Friendly error messages (no crashes on invalid input, including valid-format country codes the API has no data for)

Install

cd nager-date-mcp
pip install -e .

Configure (Hermes)

Add to your Hermes config.yaml under mcp_servers:

mcp_servers:
  nager-date:
    command: python
    args: ["-m", "nager_date_mcp.server"]

Or for Claude Desktop / other MCP clients:

{
  "mcpServers": {
    "nager-date": {
      "command": "python",
      "args": ["-m", "nager_date_mcp.server"]
    }
  }
}

Development

pip install -e ".[dev]"
python -m pytest tests/ -v

API Details

  • Source: https://date.nager.at/api/v3/
  • Auth: None
  • Rate limits: None observed (Cloudflare CDN, 7-day cache headers)
  • Year range: 1976–2076
  • Countries: 202 (ISO 3166-1 alpha-2)
  • Subdivisions: ISO 3166-2 (e.g. GB-ENG, GB-SCT, DE-BY, CA-ON)
  • Holiday types: Public, Bank, School, Authorities, Optional, Observance

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选