pl-holidays-mcp
Enables Polish public holiday lookups and business-day arithmetic (e.g., adding business days, counting business days) using the Nager.Date API, defaulting to Poland but supporting 110+ countries.
README
pl-holidays-mcp
Local MCP server for Polish public holidays and business-day arithmetic. Wraps the open Nager.Date holiday database and adds bookkeeping-friendly business-day math on top.
Part of the honest-mcp family of small, auditable, local-first MCP servers.
Why
Every Polish accountant, JDG owner, or HR person has this problem:
- "Payment term is 14 dni roboczych from invoice date — what's the actual due date?"
- "Is the client's 'termin płatności 2026-05-01' the same as
next_business_day(2026-05-01)? (No — that's Święto Pracy.)" - "Deadline for JPK_V7 is the 25th — but 2026-04-25 is a Saturday, does it slip to Monday?"
This server hands both raw holiday data and business-day arithmetic to your AI. No more spreadsheet calendars.
Supports any country Nager.Date covers (110+), but the API defaults to Poland and the bookkeeping angle is Poland-centric.
Features
Six tools:
list_holidays— all public holidays in a given yearis_holiday— is this specific date a public holiday?is_business_day— is this date Mon–Fri and not a holiday? Includes reason (weekend / holiday / business_day)count_business_days— inclusive business-day count between two datesadd_business_days— start_date + N business days = ? (N can be negative)next_holidays— upcoming N holidays from a given date
Data source
- Endpoint: date.nager.at/api/v3
- No API key
- MIT-licensed holiday data
- In-memory year cache — one round trip per year per session
Requirements
- Python 3.10+
Setup
git clone https://github.com/bartosz-kuc/pl-holidays-mcp.git
cd pl-holidays-mcp
python3 -m venv venv
./venv/bin/pip install -r requirements.txt
Register with Claude Code:
claude mcp add pl-holidays /absolute/path/to/venv/bin/python /absolute/path/to/server.py
Claude Desktop claude_desktop_config.json:
{
"mcpServers": {
"pl-holidays": {
"command": "/absolute/path/to/venv/bin/python",
"args": ["/absolute/path/to/server.py"]
}
}
}
Example usage
"Invoice issued today with 14 working-day payment term — when is it due?"
add_business_days(start_date="2026-07-22", days=14) → the due date, skipping weekends and Polish public holidays.
"How many working days between 2026-04-01 and 2026-04-30?"
count_business_days(from_date="2026-04-01", to_date="2026-04-30")
"Is May 1st 2026 a business day in Poland?"
is_business_day(date="2026-05-01") → false, reason: holiday (Święto Pracy).
Data flow
Your AI client
↕ MCP stdio
This server (Python, on your machine)
↕ HTTPS
date.nager.at (Nager.Date open holiday DB)
No cloud middle for anything but the initial holiday-date fetch. No telemetry.
Author
Bartosz Kuć — Warsaw-based developer, JDG owner running skanfirmy.pl.
-
GitHub: https://github.com/bartosz-kuc
-
Email: firma@bartosza.pl
Consulting
Available for consulting on Polish tax and business integrations (KSeF, GUS/NFZ/GIOŚ APIs, mBank data), MCP server design, and AI-assisted tooling for JDGs and small teams. See skanfirmy.pl/uslugi for productized packages (audit 3k PLN, setup 8-15k PLN, retainer 2-4k PLN/mo), or reach out via email.
License
MIT — see LICENSE.
Related
- Part of the honest-mcp family — see the family index.
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。