This server provides MCP tools to query South Korean weather and timezone information.
Weather tools (require KMA_SERVICE_KEY):
get_current_weather(location): Current observed weather (temperature, humidity, precipitation, wind) from the Korea Meteorological Administration's 초단기실황.
get_hourly_forecast(location, hours): Hourly forecast for up to 6 hours (default) or more (max 100).
get_daily_forecast(location, slots): Daily forecast for up to 3 days, including precipitation probability and min/max temperatures.
Time tools (no external dependencies):
get_current_time(timezone): Current time in a given IANA timezone (default Asia/Seoul).
convert_time(time, from_timezone, to_timezone): Convert time between timezones (accepts YYYY-MM-DD HH:MM or ISO 8601).
find_timezone(query): Search for IANA timezone names by partial match (e.g., "Seoul").
Flexible location input: Weather tools accept Korean region names (e.g., 서울, 부산광역시), partial matches (e.g., 성남시 분당구), or latitude,longitude strings. If omitted, the default is 서울.
Output & configuration: KMA weather codes are translated into human‑readable terms (e.g., SKY=1 → 맑음). Errors are returned as JSON with an 오류 field. Weather or time tools can be individually disabled via environment variables to reduce token usage.
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., "@oc-korea-weather-time-mcp 내일 아침 서울 날씨"
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.
기상청 날씨와 시간대 조회를 제공하는 MCP 서버.
소개 페이지 → https://jshsakura.github.io/oc-korea-weather-time-mcp/
uvx oc-korea-weather-time-mcp기존 korea-weather-mcp 는 개인 개발자가 2025-09 에 v0.1.0 한 번 올리고 방치했고
초단기실황만 지원한다.
자격증명(기상청 서비스 키)을 다루는 물건은 직접 관리한다는 방침.
날씨와 시간은 어차피 같이 쓰인다 — "내일 아침 서울 날씨" 를 답하려면 둘 다 필요하다.
Related MCP server: MCP Weather Server
툴 | 출처 API | 범위 |
| 초단기실황 | 지금 관측값 |
| 초단기예보 | 앞으로 6시간 |
| 단기예보 | 앞으로 3일 |
location 은 지역명(서울·인천·부산광역시), 부분 일치(성남시 분당구),
또는 위도,경도 문자열을 받는다. 생략하면 KMA_DEFAULT_LOCATION(기본 서울).
모르는 지역이면 오류 응답에 지원 목록을 실어 보낸다 — 목록 전용 툴을 두면
매 요청 프롬프트에 비용이 붙기 때문이다.
강수확률(POP)과 일최저/최고기온은 단기예보에만 있다.
툴 | 하는 일 |
| 지정 시간대의 현재 시각 |
| 시간대 간 변환 |
| IANA 시간대 이름 검색 |
시간 쪽은 파이썬 표준 zoneinfo 만 쓴다. 외부 의존이 없다.
export KMA_SERVICE_KEY="발급받은-디코딩-키" # 날씨 툴에 필수
export KMA_DEFAULT_LOCATION="서울" # 선택서비스 키는 공공데이터포털 → 기상청_단기예보 조회서비스
활용신청 → 일반 인증키(Decoding). 인코딩 키(%2B 가 섞인 것)를 넣으면
이중 인코딩으로 인증에 실패한다.
키는 환경변수로만 받는다. httpx 가 INFO 레벨에서 요청 URL 전체를 찍는데
쿼리스트링에 serviceKey 가 들어 있어 키가 로그에 평문으로 남는다.
그래서 httpx·httpcore 로거를 WARNING 으로 낮춘다.
툴 정의는 매 요청마다 프롬프트에 실린다. 필요 없는 쪽은 끄면 그만큼 가벼워진다.
export OC_KOREA_MCP_TIME=0 # 날씨 툴 3개만
export OC_KOREA_MCP_WEATHER=0 # 시간 툴 3개만# Claude Code
claude mcp add oc-korea-weather-time \
-e KMA_SERVICE_KEY=발급받은-키 \
-- uvx oc-korea-weather-time-mcp
# Hermes
hermes mcp add oc-korea-weather-time \
--command uvx --args oc-korea-weather-time-mcp \
--env KMA_SERVICE_KEY=발급받은-키격자 변환 — 기상청 API 는 위경도를 안 받고 자체 격자(nx, ny)를 쓴다. Lambert Conformal Conic 투영, 파라미터는 기상청 고시값. 서울(60,127)·부산(98,76)·제주(53,38) 표준 검증값과 일치를 확인했다.
코드 해석 — API 는 SKY=1 같은 숫자만 준다. 그대로 넘기면 LLM 이 해석을
지어내므로 서버에서 맑음 으로 풀어 넘긴다. 매핑에 없는 코드는 임의 해석하지 않고
알 수 없음(값) 으로 표시한다.
단위 — 기상청은 강수량 자리에 강수없음 같은 문자열을 섞어 보낸다.
수치일 때만 단위를 붙인다.
발표시각 — 초단기는 매시 40분 생성이라 그 전이면 한 시간 전 발표분을 쓴다. 단기예보는 하루 8회(02·05·08·11·14·17·20·23시) 발표.
오류를 예외로 던지지 않는다. 툴은 {"오류": "..."} 를 돌려준다.
LLM 이 다음 행동을 정할 수 있어야 한다.
uv venv && uv pip install -e . pytest
uv run pytest tests/ -q외부 호출 없이 격자 변환·발표시각·지역 해석·표시 변환을 검증한다. API 호출 경로는 네트워크와 키가 필요하므로 테스트에서 제외했다.
MIT
한 시간대의 시각을 다른 시간대로 변환한다.
Args:
time: 변환할 시각. YYYY-MM-DD HH:MM 또는 ISO 8601
from_timezone: 원본 IANA 시간대
to_timezone: 대상 IANA 시간대
| Name | Required | Description | Default |
|---|---|---|---|
| time | Yes | ||
| to_timezone | Yes | ||
| from_timezone | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It only gives a minimal function statement and argument formats, without mentioning edge cases, error handling, side effects, or the nature of the conversion (e.g., DST handling). It adds no behavioral insight beyond the obvious pure conversion.
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 extremely concise—a single sentence plus a compact Args list. Every element is necessary and informative, with no filler or redundancy.
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 and has an output schema, so return details are not needed. The description adequately covers the core purpose and all parameters. However, it lacks any usage context or notes on potential pitfalls (e.g., invalid timezone, DST edge cases), which would make it more complete for robust agent 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?
The description explicitly explains each parameter: time with accepted formats (`YYYY-MM-DD HH:MM` or ISO 8601), and from_timezone/to_timezone as IANA timezones. This adds significant meaning over the bare schema titles (Time, To Timezone, From Timezone) and fully compensates for the 0% schema description coverage.
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 'Converts a time in one timezone to another timezone', specifying the verb (convert), resource (time), and the from/to timezone context. It unambiguously distinguishes from siblings like get_current_time, find_timezone, and weather tools.
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 guidance is provided on when to use this tool versus alternatives. It simply states what it does without mentioning scenarios, exclusions, or references to sibling tools like get_current_time or find_timezone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
IANA 시간대 이름을 부분 문자열로 검색한다.
Args: query: 검색어 (예: Seoul, New_York, Europe)
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the partial-substring search behavior, but does not mention case sensitivity, whether multiple matches are returned, or what happens with no matches. For a simple search tool, this is adequate but could be more informative.
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 extremely concise: a single sentence plus a parameter explanation. Every word adds value, with no redundancy. It is well-structured and easy to parse.
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 parameter, and the description covers its core purpose and behavior. An output schema exists, so return values are not described in the text, which is acceptable. However, the description does not mention any filters or limitations (e.g., whether the search is case-insensitive), leaving minor gaps for a complete understanding.
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 only the parameter name and type ('query', string) with no description. The description adds meaning by defining it as a search term and giving concrete examples (Seoul, New_York, Europe), which compensates for the 0% schema coverage and helps the agent understand expected input.
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?
Description clearly states it searches IANA timezone names by partial substring, using the specific verb '검색한다' (searches). This distinguishes it from sibling tools like convert_time and get_current_time, which perform different operations.
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?
Usage is implied by the description: it is for finding IANA timezone names using partial substrings. However, no explicit guidance is given on when to prefer this over alternatives or when not to use it. Given the context of sibling tools, it is reasonable but not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
지정한 시간대의 현재 시각을 조회한다.
Args: timezone: IANA 시간대 이름 (기본 Asia/Seoul)
| Name | Required | Description | Default |
|---|---|---|---|
| timezone | No | Asia/Seoul |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden of behavioral disclosure. It indicates a read operation ('조회한다'), which implies safety, but does not add extra context such as error behavior, system-clock dependence, or rate limits. For a simple read tool this is acceptable but not rich.
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 extremely concise, consisting of one clear purpose sentence and a brief parameter explanation. It is front-loaded with the action and resource, and every word earns its place. No redundant or filler content.
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?
With only one optional parameter and an output schema present, the description covers the essential context. It clearly explains the main function and the only argument. It could improve by mentioning what happens if timezone is omitted, but the schema's default already covers that. Overall, it's complete for a tool of this simplicity.
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 0%, so the description must compensate. It does so by defining the 'timezone' parameter as an IANA timezone name with a default of Asia/Seoul, which adds meaningful semantic detail beyond the schema's generic 'string' type. This is sufficient for the single parameter.
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: to retrieve the current time in a specified timezone. It uses a specific verb, '조회한다' (retrieves), and a specific resource, '현재 시각' (current time). This distinguishes it from sibling tools like convert_time (which converts times) and find_timezone (which finds timezones).
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 getting the current time in a timezone, but does not explicitly contrast it with alternatives. No 'use this when' or 'instead of' guidance is provided, unlike the high-caliber example that names an alternative tool. The context is clear but lacks explicit exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
지금 관측된 날씨를 조회한다 (기상청 초단기실황).
기온·습도·강수형태·풍향·풍속·1시간 강수량을 돌려준다.
Args: location: 지역명 (예: 서울, 인천, 부산). 생략하면 기본 지역. '위도,경도' 형식도 받는다.
| Name | Required | Description | Default |
|---|---|---|---|
| location | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses the return fields (temperature, humidity, precipitation type, wind, precipitation amount), the input format (region name or latitude/longitude), and default behavior when location is omitted. While it doesn't mention units or error behavior, the explicit output list and input flexibility provide solid transparency for a read-only weather tool.
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 succinct and well-structured: a first sentence stating the purpose, a second listing outputs, and a compact Args section. Every sentence adds value, and the format is easy to scan.
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 (one parameter) and has an output schema, so the description need not elaborate return values. It provides enough information about inputs, outputs, and current-weather specificity. The only minor gap is the unspecified default region, but this does not undermine overall completeness.
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 only provides a bare 'location' string with a default. The description adds rich semantics: it explains the parameter accepts a place name (with examples), defaults to a specified region when omitted, and also supports 'latitude,longitude' format. This fully compensates for the schema's lack of parameter description.
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 purpose: '지금 관측된 날씨를 조회한다' (queries currently observed weather) and lists the specific data returned. This unambiguously distinguishes it from sibling tools like hourly/daily forecasts, which cover different time contexts.
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?
Usage context is implied rather than explicit. The description clarifies it provides current observations as opposed to forecasts, but it does not explicitly say 'use this for current weather, use get_daily_forecast for daily predictions.' No alternatives or exclusions are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
앞으로 3일까지의 예보를 조회한다 (기상청 단기예보).
강수확률·일최저/최고기온이 여기에만 있다.
Args: location: 지역명. 생략하면 기본 지역. slots: 돌려받을 예보시각 개수 (기본 24, 최대 100)
| Name | Required | Description | Default |
|---|---|---|---|
| slots | No | ||
| location | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the burden. It discloses the forecast range, data exclusivity, and default/slot behavior. However, it does not mention return format, error handling, or update times; the output schema covers structure but the description provides limited behavioral nuance beyond parameters.
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 two short sentences plus an Args list, each line containing unique and necessary information. It is front-loaded with the main purpose and immediately provides key differentiators, with 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?
For a simple tool with an output schema and two optional parameters, the description covers purpose, differentiators, and parameter semantics. It doesn't address error scenarios or response format, but given the low complexity and presence of an output schema, 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?
The schema has 0% description coverage, so the Args block fully compensates. It explains 'location' as region name with default region behavior, and 'slots' as number of forecast times with default 24 and max 100. This adds essential meaning beyond the bare schema properties.
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 does '앞으로 3일까지의 예보를 조회한다' (retrieves forecast up to 3 days) from the KMA, with a specific resource and action. It also distinguishes itself by noting that precipitation probability and daily min/max are only available here, which differentiates it from sibling tools.
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?
It explicitly states that precipitation probability and daily min/max temperatures are only found here, guiding the user to use this tool when those fields are needed. It implies which alternatives exist but does not name them directly, so it's clear but not fully exhaustive.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
앞으로 6시간까지의 시간별 예보를 조회한다 (기상청 초단기예보).
Args: location: 지역명. 생략하면 기본 지역. hours: 돌려받을 시각 개수 (기본 6, 최대 100)
| Name | Required | Description | Default |
|---|---|---|---|
| hours | No | ||
| location | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden of behavioral disclosure. It does add context about the data source and time range, and it explains parameter defaults and limits, but it does not disclose potential errors, rate limits, or the nature of output beyond what the output schema would show. The description is informative 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 extremely concise, with the primary purpose front-loaded in a single clause followed by a compact Args list. Every sentence adds information, with no repetition or 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?
Given the tool's simplicity and the presence of an output schema, the description adequately covers the essential context: source, time range, parameters, and defaults. It could be more complete by mentioning potential error conditions or format specifics, but for a straightforward forecast lookup, it is sufficient.
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 0%, but the description compensates by providing an 'Args' section that explains 'location' as region name with default behavior and 'hours' as the number of time slots (default 6, max 100). This adds meaningful semantic value beyond the bare schema properties and defaults.
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 purpose: '앞으로 6시간까지의 시간별 예보를 조회한다' (retrieves hourly forecast up to 6 hours ahead), with a specific resource (hourly forecast) and source (기상청 초단기예보). It distinguishes itself from siblings like get_daily_forecast and get_current_weather by specifying hourly granularity.
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 by defining the forecast scope (hourly, up to 6 hours) and parameter meaning, but it does not explicitly state when to choose this tool over siblings or include any exclusions. Context is present, but no direct guidance on alternatives is given.
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.
v0.1.0convert_timefind_timezoneget_current_timeget_current_weatherget_daily_forecastget_hourly_forecastScored across 6 tools
Each tool targets a distinct operation: time lookup, time conversion, timezone search, current weather, hourly forecast, and daily forecast. The two 'get_current_*' tools are clearly separated by domain (time vs weather) and description.
All tool names follow a verb_noun pattern (get_*, convert_*, find_*). The verbs are semantically appropriate and the pattern is consistent across both domains.
6 tools is well-scoped for a combined time and weather server. Each tool covers a necessary function without unnecessary bloat.
The time domain covers current time, conversion, and timezone search. The weather domain covers current observations, hourly forecast, and daily forecast. Minor gaps like weather alerts or location search exist but core workflows are covered.
Hosted MCP server for Xweather weather data: conditions, forecasts, alerts, and more.
An MCP server for weather information by @kulybaba
An MCP server for weather information by @kulybaba
Timezone MCP — wraps WorldTimeAPI (free, no auth)