Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@holidays-mcp what are the public holidays in the US in 2026?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Real, official public holiday data for ~100 countries, free, in one command.
pip install holidays-mcp # or: uvx holidays-mcpThen ask your agent: "what are the public holidays in the US in 2026?" or "is December 25th 2026 a holiday in the US?"
No API key. No signup. Free.
Tool | What the model sees it for |
| Full list of a country's public holidays for a given year. "What are the holidays in Germany in 2026?", planning around a holiday calendar. |
| Whether one specific date is a public holiday, and its name if so. "Is Dec 25 2026 a holiday in the US?", "is the office closed on this date?" |
Country codes are 2-letter ISO (US, GB, DE, FR, JP, ...) — Nager.Date covers roughly 100 countries with official holiday calendars, not every country worldwide. Dates are YYYY-MM-DD.
Related MCP server: inday-api
> is_public_holiday("US", "2026-12-25")
{
"date": "2026-12-25",
"country_code": "US",
"country_name": "United States",
"is_holiday": true,
"holiday": {
"local_name": "Christmas Day",
"name": "Christmas Day",
"types": ["Public", "Bank"]
},
"attribution": "Public holiday data by Nager.Date (date.nager.at)"
}> get_public_holidays("US", 2026)
{
"country_code": "US",
"country_name": "United States",
"year": 2026,
"count": 17,
"holidays": [
{"date": "2026-01-01", "local_name": "New Year's Day", "name": "New Year's Day", "types": ["Public", "Bank"]},
{"date": "2026-01-19", "local_name": "Martin Luther King, Jr. Day", "name": "Martin Luther King, Jr. Day", "types": ["Public", "Bank"]},
...
],
"attribution": "Public holiday data by Nager.Date (date.nager.at)"
}This server is part of the Lulu Ads network:
tool results may carry one clearly labeled, disclosed sponsored data field
(never instructions, never hidden). That sponsorship pays the hosting, so the
lookup stays free. Fail-open by design — if the ads backend is slow, down,
or (as with a local install) has no credentials at all, the tools behave
exactly like an unmonetized server.
Run your own MCP? The same one-line integration is open to every publisher — getlulu.dev/publishers, 70% rev share.
Public holiday data by Nager.Date, a free, keyless, community-maintained holiday calendar API. This project is not affiliated with Nager.Date.
pip install fastmcp lulu-ads httpx uvicorn
MCP_TRANSPORT=http HOLIDAYS_LOCAL_DEV=1 python server.py # serves http://localhost:8080/holidays/mcpFull list of official public holidays for a country in a given
year. Use for "what are the holidays in Germany in 2026", planning
around a country's holiday calendar, or any "list the holidays for X"
question. country_code is a 2-letter ISO code (US, GB, DE, FR, JP,
...) -- roughly 100 countries are covered, not every country
worldwide. Returns each holiday's date, local name, English name, and
type (e.g. Public, Bank, Observance).
| Name | Required | Description | Default |
|---|---|---|---|
| year | Yes | ||
| country_code | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the read-only nature is known. The description adds useful behavioral context beyond that, including the return format (date, local name, English name, type) and the country coverage limitation. It does not mention error handling or constraints on the year parameter, but for a simple read tool this is reasonably transparent.
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 composed of three sentences: the first states the core purpose, the second gives usage examples, and the third provides parameter and return details. Each sentence adds value and the text is front-loaded with the main purpose. It is slightly longer than strictly necessary, but remains concise and well-structured.
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?
For a simple read-only tool with two parameters and an existing output schema, the description provides complete context: purpose, usage examples, country_code format, coverage limitation, and return fields. It also implicitly differentiates from the sibling tool by focusing on listing, so the agent can select and invoke it correctly. No significant gaps remain.
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?
The schema provides no descriptions for the two parameters, and schema coverage is 0%. The description compensates by explaining `country_code` is a 2-letter ISO code with examples (US, GB, DE, FR, JP, ...) and that only about 100 countries are covered. The `year` parameter is left as a simple integer, but its meaning is self-evident from the tool purpose. This partial compensation is helpful, though not exhaustive.
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 that the tool returns a full list of official public holidays for a country in a given year. The verb 'get' is implied by the name, but the description uses 'Full list' to specify the scope, distinguishing it from the sibling tool is_public_holiday which likely checks a single date. It also gives example queries, making the purpose unmistakable.
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 provides specific example use cases like 'what are the holidays in Germany in 2026' and 'planning around a country's holiday calendar', which clearly indicate when to use the tool. It also states a limitation (roughly 100 countries are covered), which sets expectations. However, it does not explicitly mention when not to use it or name the alternative tool for single-day checks, so it lacks explicit exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Checks whether one specific date is a public holiday in a country,
and names it if so. Use for "is Dec 25 2026 a holiday in the US",
"is the office closed on this date", or any single-date holiday check
-- prefer this over get_public_holidays when the question is about
just one day. country_code is a 2-letter ISO code; date is
YYYY-MM-DD. Returns whether it's a holiday and, if so, its name.
| Name | Required | Description | Default |
|---|---|---|---|
| date | Yes | ||
| country_code | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint annotation, the description adds that the tool returns a boolean holiday status and the holiday's name if applicable. It also clarifies that it checks exactly one date, which is useful behavioral context. No contradiction with annotations.
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 concise yet information-dense, covering purpose, usage, parameter formats, and return behavior in just a few sentences. It is front-loaded with the core function and contains no filler.
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?
For a simple two-parameter, read-only tool with an output schema, the description covers all necessary aspects: what it does, when to use it, parameter semantics, and return behavior. It is fully complete without being verbose.
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?
Despite 0% schema coverage, the description explicitly defines both parameters: country_code as a 2-letter ISO code and date as YYYY-MM-DD. This fully compensates for the lack of schema descriptions, providing precise format and meaning.
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?
Clearly states the tool checks whether one specific date is a public holiday in a country and names it if so. The verb 'checks' and specific resource (single date + country) make the purpose unambiguous. It also distinguishes from sibling get_public_holidays by noting the single-day focus.
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?
Explicitly provides usage examples and says to prefer this over get_public_holidays for single-date checks. This gives clear when-to-use guidance and names the alternative, satisfying the highest bar for this dimension.
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.
v0.1.0get_public_holidaysis_public_holidayScored across 2 tools
The two tools have completely distinct purposes: one lists all holidays for a country and year, the other checks a single date. There is no overlap or ambiguity between them.
Both names follow a consistent verb_noun pattern with lower_snake_case. 'get_public_holidays' and 'is_public_holiday' are clear and predictable, even though they use different verbs appropriate to their actions.
With only two tools, the server feels thin, falling into the 'borderline' category. However, the count is reasonable for the narrow domain of public holiday lookups.
The domain is fully covered with the two core operations: listing all holidays and checking a specific date. As a read-only service, there are no obvious gaps or missing operations.
Public holidays for 100+ countries — by year, or the next ones coming up. Via Nager.Date.
Free, keyless public holidays lookup for any country and year, plus single-date holiday checks.
Public holiday data for 30+ countries. Check holidays, working days and calendars via AI assistants.
Holidays MCP — wraps Nager.Date API (free, no auth)
