中国の法定祝日・振替出勤日を照会する MCP（Model Context Protocol）サーバー。ゼロ依存、オフライン対応、すぐに使えます。
データソース：国務院弁公庁『2025年の一部祝祭日の手配に関する通知』『2026年の一部祝祭日の手配に関する通知』（国弁発明電）。
✅ ゼロ依存：純粋な Node.js 標準ライブラリ、node >= 18 でそのまま動作
✅ stdio トランスポート、MCP 2024-11-05 プロトコル準拠
✅ 2025年・2026年の完全なデータを収録（全振替出勤日を含む）
✅ 2つのツール：query_holiday（特定日を照会）、list_holidays（年間を一覧表示）
Related MCP server: Nager MCP v202 MCP Server
node src/server.mjs # 直接运行
npm start # 或通过 npm script
node tests/smoke.mjs # 冒烟测试claude_desktop_config.json を編集：
{
"mcpServers": {
"cn-holiday": {
"command": "node",
"args": ["C:\\path\\to\\cn-holiday-mcp\\src\\server.mjs"]
}
}
}ツール | パラメータ | 例 |
|
|
|
|
|
|
2026-02-14 → 「春節の振替出勤日、出勤が必要」
2026-10-05 → 「国慶節の休暇、合計7日間」
2026-03-10 → 「通常の平日」
旧暦/こよみ/二十四節気（万年暦）
2027年以降のデータ（公式発表次第更新）
企業向けシフトAPI、サブスクリプション制（HTTP + token）
多言語の祝日
cn-holiday-mcp は、中国の祝日と振替出勤日（调休）のためのゼロ依存のMCPサーバーです。国務院の公式通知に基づき2025〜2026年をカバー。APIキー不要、ネットワーク呼び出し不要、完全オフライン。
ツール
query_holiday — 指定した日付（YYYY-MM-DD）が祝日か、振替出勤日か、通常の平日かを判定
list_holidays — 振替出勤日を含む年間スケジュールを一覧表示
実行
node src/server.mjs # Node.js >= 18, nothing to installインストール — Claude Desktop の claude_desktop_config.json：
{
"mcpServers": {
"cn-holiday": {
"command": "node",
"args": ["C:\\path\\to\\cn-holiday-mcp\\src\\server.mjs"]
}
}
}ロードマップ — 旧暦/二十四節気；2027年以降のスケジュール；企業向けシフトAPI（サブスクリプション）；他国対応
MIT
列出某一年（或全部已收录年份）的法定节假日安排，包括放假区间、天数与调休上班日。
| Name | Required | Description | Default |
|---|---|---|---|
| year | No | 年份，如 "2026"；缺省时返回全部已收录年份 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It clearly discloses that the tool returns holiday periods, day counts, and adjusted work days, and that omitting the year returns all recorded years. This goes beyond a simple 'list holidays' to specify the output content, though it does not mention side effects or read-only nature (implicit).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is concise and front-loaded. It starts with the action and resource, provides the scoping condition, and enumerates the output contents. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with one optional parameter and no output schema. The description covers the main functionality and parameter behavior. It does not specify the exact return format (e.g., array structure), but given minimal complexity and the presence of content details, it is sufficiently complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% for the 'year' parameter, so the schema already explains it. The description paraphrases the parameter (year or all years) without adding significant new meaning. It is adequate but does not enhance beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists statutory holiday arrangements for a given year or all recorded years, specifying included details (holiday periods, number of days, adjusted working days). This is a specific verb+resource that distinguishes it from a generic 'query' tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool vs the sibling tool 'query_holiday'. The description only implies its use for listing holidays, but does not mention alternatives or exclusions. It gives a default behavior hint (returns all years if year omitted), but no when-to-use or when-not-to-use comparison.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
查询某一天（YYYY-MM-DD）是法定节假日、调休上班日还是普通工作日。返回节假日名称、放假区间和该区间内的调休上班日。
| Name | Required | Description | Default |
|---|---|---|---|
| date | Yes | 日期，格式 YYYY-MM-DD，例如 2026-02-17 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It discloses the output categories and return fields but does not mention error handling, edge cases (e.g., invalid dates), or any side effects. For a read-only query, this is adequate but not exhaustive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that front-loads the purpose and key return data. There is zero fluff, and every clause contributes meaning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (1 param, no output schema, no annotations), the description adequately covers what it does and what it returns. It could add notes on behavior for non-holiday days or invalid inputs, but overall it is sufficiently complete for an agent to use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% — the date parameter has its own format and example. The description repeats the format (YYYY-MM-DD) but adds no extra semantic value beyond the schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: querying whether a specific date is a legal holiday, compensatory workday, or ordinary day. It also specifies the return data (holiday name, interval, compensatory days), which distinguishes it from the sibling list_holidays that likely lists all holidays.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for a single date ("查询某一天") but does not explicitly mention when to use this over the sibling tool list_holidays, nor any exclusion criteria. The context is understandable but lacking explicit guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0list_holidaysquery_holidayScored across 2 tools
query_holiday targets a single specific date while list_holidays returns full annual arrangements, so their purposes are clearly distinct. There is no practical overlap that would cause an agent to misselect.
Both tool names follow a consistent verb_noun pattern: query_holiday and list_holidays. The only minor difference is singular versus plural noun, which is natural and does not harm consistency.
Two tools is slightly thin, but each tool earns its place for the server's narrow read-only purpose. It falls at the borderline edge of the typical 3-15 tool range.
The server covers the core holiday use cases: checking a specific day and listing a year's holiday schedule. Minor gaps exist, such as date-range lookups or upcoming-holiday queries, but they are workable conveniences rather than critical dead ends.
MCP server for China Railway 12306 ticket availability: schedules and seats by Chinese station name.
MCP server for public_holidays_mcp
MCP server providing attendance data queries via the CloudTime API.
China facts a server outside China cannot get: real mainland reachability, 调休 holidays, ID/phone val