How do I use taiwan-weather-mcp?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@taiwan-weather-mcp 台北未來36小時天氣如何？" 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.

taiwan-weather-mcp

by tun0000

Overview Schema Related Servers Score Discussions

Python

Remote

taiwan-weather-mcp

台灣即時天氣預報、天氣特報與有感地震查詢的 MCP（Model Context Protocol）server，讓 Claude Desktop / Claude Code 直接查中央氣象署的開放資料。

使用官方 mcp Python SDK 的 FastMCP （SDK v2 起更名為 MCPServer，本專案使用穩定版 v1 系列），stdio transport。資料來源：中央氣象署開放資料平臺。

提供的工具

工具	說明	參數
`get_forecast`	某縣市未來 36 小時天氣預報（天氣現象、降雨機率、氣溫區間、舒適度）。縣市名稱有模糊對應：「台中」→「臺中市」、「Taipei」→「臺北市」；「新竹」「嘉義」會同時回傳市與縣	`city`：縣市名稱
`get_weather_warnings`	目前生效中的天氣特報（颱風、豪雨、低溫、強風等），依特報種類彙整影響縣市；沒有特報時會明確說明	無
`get_recent_earthquakes`	最近幾筆顯著有感地震（時間、規模、深度、震央、各縣市最大震度摘要）	`limit`：筆數 1–10，預設 5

對應的 CWA dataset：F-C0032-001（36 小時預報）、W-C0033-001（天氣特報）、E-A0015-001（顯著有感地震報告）。

Related MCP server: Weather MCP Server

1. 申請 CWA API 授權碼（免費）

到中央氣象署開放資料平臺點右上角「登入/註冊」，註冊會員（一般 Email 即可，即時核發）。
登入後到會員資訊 → API授權碼。
點「取得授權碼」，複製形如 CWA-XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX 的字串。

授權碼只透過環境變數 CWA_API_KEY 讀取，不要寫進任何檔案。本機開發可複製 .env.example 為 .env 填入（.env 已被 .gitignore 排除）。

2. 安裝

先安裝 uv：

# Windows（PowerShell）
winget install astral-sh.uv
# WSL / Linux / macOS
curl -LsSf https://astral.sh/uv/install.sh | sh

然後：

git clone https://github.com/tun0000/taiwan-weather-mcp.git
cd taiwan-weather-mcp
uv sync          # 會自動下載 Python 3.12 與所有依賴

3. 在 Claude Code 使用

# Windows（PowerShell，路徑換成你 clone 的位置）
claude mcp add taiwan-weather -e CWA_API_KEY=你的授權碼 -- uv --directory "C:\path\to\taiwan-weather-mcp" run server.py

# WSL / Linux / macOS（repo 需 clone 在該環境內）
claude mcp add taiwan-weather -e CWA_API_KEY=你的授權碼 -- uv --directory ~/taiwan-weather-mcp run server.py

加好後用 claude mcp list 確認，然後在對話中直接問「台中明天天氣如何？」即可。

4. 在 Claude Desktop（Windows）使用

設定檔位置：%APPDATA%\Claude\claude_desktop_config.json （Claude Desktop → 設定 → 開發人員 → 編輯設定檔）。

改完設定檔請從系統匣完全結束 Claude Desktop 再重開；檔案須以 UTF-8 儲存。

寫法 A：server 在 WSL 內，透過 `wsl.exe` 橋接

前置（在 WSL 內執行一次）：

curl -LsSf https://astral.sh/uv/install.sh | sh        # 安裝 uv
git clone https://github.com/tun0000/taiwan-weather-mcp.git ~/taiwan-weather-mcp
cd ~/taiwan-weather-mcp && uv sync

repo 請放 WSL 自己的檔案系統（如 ~/），不要放 /mnt/c/...，速度差很多。

{
  "mcpServers": {
    "taiwan-weather": {
      "command": "wsl.exe",
      "args": [
        "-e", "bash", "-c",
        "CWA_API_KEY=你的授權碼 exec $HOME/.local/bin/uv --directory $HOME/taiwan-weather-mcp run server.py"
      ]
    }
  }
}

兩個常見地雷這個寫法都避開了：

Claude Desktop 的 env 區塊不會自動穿透 WSL 邊界，所以金鑰用行內環境變數帶入。若不想讓金鑰出現在 args，可改用 WSLENV 轉送：

{
  "mcpServers": {
    "taiwan-weather": {
      "command": "wsl.exe",
      "args": ["-e", "/home/你的WSL帳號/.local/bin/uv",
               "--directory", "/home/你的WSL帳號/taiwan-weather-mcp",
               "run", "server.py"],
      "env": { "CWA_API_KEY": "你的授權碼", "WSLENV": "CWA_API_KEY/u" }
    }
  }
}

用非登入 shell（bash -c 而非 bash -lc）＋ uv 絕對路徑：登入 shell 的 profile 若有任何輸出，會污染 stdout 打斷 MCP 協定。

寫法 B：直接在 Windows 端用 Python/uv 執行

前置：Windows 裝好 uv（見上），repo clone 在 Windows 檔案系統並 uv sync。

{
  "mcpServers": {
    "taiwan-weather": {
      "command": "C:\\Users\\你的帳號\\.local\\bin\\uv.exe",
      "args": ["--directory", "C:\\path\\to\\taiwan-weather-mcp", "run", "server.py"],
      "env": { "CWA_API_KEY": "你的授權碼" }
    }
  }
}

command 建議填 uv 的完整路徑（Claude Desktop 不一定繼承你的 PATH）。在 PowerShell 執行 (Get-Command uv).Source 查詢實際位置（winget 安裝的路徑會在 ...\WinGet\Packages\astral-sh.uv_...\uv.exe）。 JSON 內的反斜線要寫成 \\。

5. 示範對話

36 小時天氣預報（「台中這兩天天氣怎樣？」）

36小時預報示範

天氣特報（「現在有什麼天氣警報嗎？」）

天氣特報示範

近期有感地震（「最近有地震嗎？」）

有感地震示範

6. 開發

uv run pytest                                          # 離線測試（fixtures）
uv run --env-file .env python scripts/explore_api.py   # 實測 CWA API、重錄 fixtures
uv run --env-file .env python scripts/smoke_test.py    # stdio 起 server 實呼叫三個 tool

專案結構：

server.py                  # MCP server 入口（FastMCP + 3 個 tool）
taiwan_weather/
  api.py                   # CWA API 呼叫（唯一做網路 I/O 的模組）
  cities.py                # 縣市名稱模糊對應（純函式）
  formatters.py            # JSON → 精簡繁中文字（純函式）
  errors.py                # 錯誤類別與所有使用者訊息
scripts/explore_api.py     # 實測 API、錄製 tests/fixtures
scripts/smoke_test.py      # stdio 端對端煙霧測試
tests/                     # pytest（unit + in-memory 整合測試）

資料來源與授權

氣象資料：中央氣象署開放資料平臺，依政府資料開放授權條款使用。
程式碼：MIT License。

安全性

授權碼只從環境變數 CWA_API_KEY 讀取，程式碼與 repo 中不含任何金鑰。
.env 已被 .gitignore 排除；.env.example 僅含佔位字串。

Available Tools

3 tools

get_forecastA

查詢台灣某縣市未來 36 小時天氣預報。

回傳三個時段的天氣現象、降雨機率、氣溫區間與舒適度。
縣市名稱接受常見寫法，例如「台中」「臺北市」「高雄」「Taipei」；
「新竹」「嘉義」同時對應市與縣，會一次回傳兩者。

Args:
    city: 縣市名稱（台灣 22 縣市，中英文皆可）。

ParametersJSON Schema

Name	Required	Description	Default
`city`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It discloses the return format (three periods), the specific data fields, and the special handling for ambiguous city names. It does not mention rate limits or authentication, but for a simple query tool, this is sufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is five sentences, front-loaded with purpose, then return data, examples, and parameter documentation. No fluff, each sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema (not shown), the description still covers the input and output adequately. It specifies the time period, data fields, and city name handling, making it complete for a simple forecast tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% (only type string), and the description adds rich semantics: accepted city names (Chinese and English), examples, and the behavior for ambiguous names like 新竹/嘉義 returning both city and county. This fully compensates for the lack of schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it queries the 36-hour weather forecast for a city in Taiwan, listing the returned fields (weather phenomena, rain probability, temperature range, comfort level) and handling ambiguous city names. It is a specific verb+resource and distinct from siblings like get_recent_earthquakes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool versus alternatives, but it provides context by listing examples and noting ambiguous city name behavior. It implies usage for weather forecasts but offers no exclusion criteria or comparisons to siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_recent_earthquakesA

查詢最近幾筆顯著有感地震報告。

每筆包含發生時間、規模、深度、震央位置與各縣市最大震度摘要。

Args:
    limit: 回傳筆數（1–10，預設 5）。

ParametersJSON Schema

Name	Required	Description	Default
`limit`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Describes returned fields and argument range/default, but does not specify the recency window or any rate limits/auth requirements. Since no annotations, description carries full burden; missing details on time range.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Very concise: two sentences plus parameter list. Purpose is front-loaded, no redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Explains result fields and parameter, but does not specify time window for 'recent'. Output schema exists so return values are documented elsewhere. Still, could be more precise about recency.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has no description for limit parameter, but description adds range (1–10) and default (5), significantly improving understanding beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it returns recent significant earthquake reports with specific fields (time, magnitude, depth, epicenter, intensity summary). This distinguishes it from siblings which are weather-related.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit when-to-use vs alternatives, but siblings are weather tools so context implies use for earthquakes. Could mention that it only includes significant earthquakes.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_weather_warningsA

查詢目前生效中的天氣特報（颱風、豪雨、大雨、低溫、強風等）。

依特報種類彙整影響縣市與有效時間；若全臺皆無生效中的警特報，會明確回覆「目前全臺無生效中的天氣警特報」。

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.5/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. It discloses that warnings are grouped by type, includes location and time, and specifies the exact response when no warnings are active. This provides sufficient transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, front-loaded with purpose, and every sentence adds value. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given zero parameters and an output schema (which the description complements by explaining return behavior), the description is complete. It covers the main functionality and edge case of no active warnings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are no parameters, so schema coverage is 100%. Per rubric, 0 parameters yields a baseline of 4. The description adds no parameter information but none is needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool queries currently active weather warnings, lists examples (typhoon, heavy rain, etc.), and specifies grouping by warning type. It naturally distinguishes from siblings 'get_forecast' and 'get_recent_earthquakes'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for retrieving current warnings but does not explicitly advise when to use versus alternatives. However, given sibling names, the context is clear enough for an AI agent.

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. Dates show when Glama detected each change.

3 tool updatesv0.1.0Jul 14, 2026
- First observedget_forecast
- First observedget_recent_earthquakes
- First observedget_weather_warnings

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.3/5.0

Disambiguation5/5

Each tool targets a distinct weather-related domain: forecasts, earthquakes, and warnings, with no overlapping functionality.

Naming Consistency5/5

All tools follow a consistent 'get_' prefix with snake_case, making naming predictable and uniform.

Tool Count4/5

Three tools cover the main weather information needs for Taiwan, though a few additional areas like current conditions might be expected.

Completeness4/5

The tool set covers key weather data (forecasts, earthquakes, warnings), but lacks real-time conditions or specific weather alerts beyond the broad categories.

Maintenance

ActivityMaintained

ResponsivenessSyncing

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

weather-mcp
io.github.kulybaba
An MCP server for weather information by @kulybaba
Weather Services Location Services
2
Weather MCP
io.github.kulybaba
An MCP server for weather information by @kulybaba
Weather Services Location Services
2
Xweather Weather MCPOAuth
com.xweather
Hosted MCP server for Xweather weather data: conditions, forecasts, alerts, and more.
Weather Services Open Data
1
DaedalMap Disaster and Geospatial Data A
com.daedalmap
Geospatial MCP server for earthquake, tsunami, volcano, disaster, and FX data queries.
Government Data Open Data Location Services
3022

Related MCP Servers

Node.js MCP Weather Server
Weather Services Cloud Platforms
Azure-Samples
F
license
Not graded
quality
D
maintenance
An MCP server that provides weather information like forecasts and alerts for US locations using the National Weather Service API.
Updated 7 months ago (2026-02-14 11:36 UTC)
5
-
Weather MCP Server
Weather Services Search
agentventure
F
license
B
quality
D
maintenance
An MCP server that provides weather information and alerts for US locations using the National Weather Service API, enabling retrieval of weather forecasts and active weather alerts.
Updated a year ago (2025-06-19 00:48 UTC)
2
-
AMap Weather MCP
Weather Services Search Location Services
KaguyaRing
A
license
Not graded
quality
D
maintenance
An MCP server that provides real-time weather information, 4-day forecasts, and city search functionality for Chinese cities via the AMap API. It enables users to query weather data using city names or administrative codes through natural language interactions.
Updated 10 months ago (2025-10-26 11:42 UTC)
1
MIT
MCP Weather Free
Weather Services Search Open Data
microagents
A
license
Not graded
quality
D
maintenance
An MCP server that provides real-time weather data, hourly forecasts, and daily summaries using the free Open-Meteo API with no API key required. It enables users to search for weather conditions by specific coordinates or city names across multiple measurement units.
Updated a year ago (2025-07-03 07:31 UTC)
1
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/tun0000/taiwan-weather-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

taiwan-weather-mcp

提供的工具

1. 申請 CWA API 授權碼（免費）

2. 安裝

3. 在 Claude Code 使用

4. 在 Claude Desktop（Windows）使用

寫法 A：server 在 WSL 內，透過 wsl.exe 橋接

寫法 B：直接在 Windows 端用 Python/uv 執行

5. 示範對話

6. 開發

資料來源與授權

安全性

Available Tools

Output Schema

Output Schema

Output Schema

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

寫法 A：server 在 WSL 內，透過 `wsl.exe` 橋接