weather
Cline과 MCP를 이용한 날씨 도구 호출
LLM이 실제 날씨 데이터를 가져올 수 있게 해주는 작은 Python MCP 서버입니다.
사용자가 Cline에서 날씨 질문을 하면, LLM은 날씨 도구를 호출할지 결정하고 필요한 인자를 생성해 이 서버로 요청을 보냅니다. 서버는 미국 국립기상청(NWS)에서 데이터를 가져오며, LLM은 그 결과를 이용해 최종 답변을 작성합니다.
작동 원리
User question
-> Cline sends the question and tool definitions to the LLM
-> The LLM selects a weather tool and generates its arguments
-> Cline calls the Python MCP server
-> The server fetches real data from api.weather.gov
-> The LLM turns the tool result into a natural-language answerRelated MCP server: Weather MCP Server
기술 스택
Python 3.14
MCP Python SDK
Cline (MCP 클라이언트 및 LLM 호스트)
데모용 DeepSeek 모델을 사용하는 OpenRouter
HTTPX
미국 국립기상청 API
uv
도구
get_forecast
미국의 한 위치에 대한 다음 5개 예보 기간을 가져옵니다.
{
"latitude": 40.7128,
"longitude": -74.006
}get_alerts
미국의 한 주에 대한 현재 기상 특보를 가져옵니다.
{
"state": "NY"
}설정
요구 사항:
Python 3.14
Cline이 설치된 Visual Studio Code
Cline에 설정된 도구 호출 가능한 LLM용 API 키
프로젝트 설치:
git clone <https://github.com/yang648557392/weather-mcp-tool-calling.git>
cd weather
uv syncMCP 서버를 Cline의 MCP 설정에 추가하세요. 경로는 이 프로젝트의 절대 경로로 바꿔 주세요:
{
"mcpServers": {
"weather": {
"command": "uv",
"args": ["--directory", "/absolute/path/to/weather", "run", "weather.py"],
"disabled": false
}
}
}Cline에서 MCP 서버를 재시작하면 Cline이 get_forecast와 get_alerts를 자동으로 발견합니다.
Cline이 uv를 찾지 못한다면, 다음 명령이 반환한 절대 경로로 "uv"를 대체하세요:
which uv사용 방법
Cline에 다음과 같은 질문을 해보세요:
What will the weather be like in New York tomorrow?
Are there any active weather alerts in California?Cline은 선택된 도구, 그 도구의 인자, 도구 결과, 그리고 LLM의 최종 응답을 보여줍니다.
제한 사항
NWS API는 미국 국립기상청이 서비스하는 지역의 위치에서만 지원됩니다.
LLM은 위치 이름을 좌표로 변환하는 책임이 있습니다.
LLM 호스트 및 MCP 클라이언트로 Cline이 필요합니다.
공급자 API 키는 Cline에 저장되며 이 저장소에 커밋해서는 안 됩니다.
저자
Mingzhe Yang
Available Tools
2 toolsget_alertsA
Get weather alerts for a US state.
Args: state: Two-letter US state code (e.g. CA, NY)
| Name | Required | Description | Default |
|---|---|---|---|
| state | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. 'Get' implies a read-only operation, but the description does not explicitly state side-effect-free behavior or any caveats about alert types or data source. It is not misleading, but it adds minimal behavioral context beyond what the name implies.
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 a front-loaded purpose statement followed by a compact Args block. Every sentence earns its place and there is 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?
With a single well-documented parameter, an output schema, and no siblings, the description plus schema fully covers what an agent needs to invoke the tool correctly. No missing context for this simple operation.
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%, yet the description fully compensates by specifying the parameter format ('Two-letter US state code') and providing concrete examples ('CA, NY'). This adds real meaning beyond the raw schema type string.
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 states a specific verb ('Get'), a clear resource ('weather alerts'), and a clear scope ('US state'). It is unambiguous and leaves no doubt about what the tool does, even without siblings to differentiate from.
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?
There are no sibling tools, so explicit routing guidance is unnecessary. The description clearly implies usage: when you need weather alerts for a US state. It lacks explicit exclusions, but nothing is misleading or missing for a tool of this simplicity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_forecastC
Get weather forecast for a location.
Args: latitude: Latitude of the location longitude: Longitude of the location
| Name | Required | Description | Default |
|---|---|---|---|
| latitude | Yes | ||
| longitude | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, so the description must carry behavioral context. It only says 'get' a forecast and gives no indication of units, time range, coordinate format, or whether this is a read-only operation. Nothing contradicts annotations, but little is disclosed beyond the basic action.
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 short and the core purpose is front-loaded. The Args block is somewhat redundant with the schema but does not add significant bloat, keeping the overall entry compact.
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 description provides the essential call requirements (latitude and longitude) and the presence of an output schema reduces the need to document return values. However, it omits practical context like expected coordinate units, available forecast periods, and why an agent would choose this over get_alerts.
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 Args section repeats the parameter names with minimal glosses ('Latitude of the location'), adding almost no meaning beyond the schema titles. Since schema description coverage is 0%, the description should compensate with coordinate format or range details, but it does not.
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 uses a clear verb and resource: 'Get weather forecast for a location'. It does not explicitly mention the sibling get_alerts, but the forecast-vs-alerts distinction is clear enough from the domain.
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 given about when to use this tool instead of get_alerts, nor are any exclusions or alternative conditions provided. The intended usage is only implied by the tool name and description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
2 tool updates
v0.1.0- First observed
get_alerts - First observed
get_forecast
TDQS
Scored across 2 tools
The two tools are clearly distinct: get_alerts retrieves weather warnings for a state, while get_forecast retrieves forecast data by coordinates. There is no overlap in their inputs or outcomes.
Both tools follow the same 'get_noun' pattern, with get_alerts and get_forecast. The naming is predictable and consistent.
With only two tools, the server is minimal and borderline scoped. While this could be fine for a specialized alerts/forecast service, it feels thin for a general weather service and does not reach the 3-15 tool sweet spot.
A weather service would typically include current conditions, hourly/daily details, or location-based lookup beyond forecast and alerts. The absence of these leaves significant gaps for users expecting general weather coverage.
Maintenance
Related MCP Connectors
Get US weather forecasts, active alerts, and current observations.
US weather & geo for AI agents: forecasts, alerts, earthquakes, elevation, geocoding. No keys.
US weather & geo for AI agents: forecasts, alerts, earthquakes, elevation, geocoding. No keys.
US weather for AI agents: active NWS alerts by state, 5-period forecasts by lat/lon. Paid per call.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables AI assistants to access real-time US weather forecasts and alerts through the National Weather Service API.29 npmMIT
- FlicenseBqualityDmaintenanceProvides real-time US weather alerts and forecasts by integrating with the National Weather Service API. It enables AI assistants to fetch state-specific alerts and detailed local forecasts using geographic coordinates.21-
- FlicenseNot gradedqualityDmaintenanceProvides weather forecasts and alerts for US locations via the National Weather Service API, enabling AI assistants to deliver real-time weather information.16 npm-
- FlicenseNot gradedqualityDmaintenanceExposes tools for retrieving weather forecasts and alerts using the National Weather Service API.-