Atmy air quality

ai.atmy由 atmy.ai 發布官方發布者v1.1.0更新於 Oct 29, 2026

PM2.5 of 300+ cities: now, history, forecast, rankings; 12 000 sensors with a quality rating.

已驗證Streamable HTTP可網頁執行位置與生活資料與分析

概覽

AI 產生的概覽

Atmy 空氣品質讓助理取得 300 多個城市與 12000 個感測器的 PM2.5 資料:目前數值、2017 年以來的歷史、排名與天氣背景。

可以做什麼
  • 依任意語言的城市名稱、國家、slug 或座標尋找城市,並列出感測器網路及其感測器數量與授權。
  • 讀取目前 PM2.5 及其美國 EPA 等級和目前天氣,以及 2017 年以來的逐日歷史,或含年度均值與紀錄月份的逐月歷史。
  • 取得城市未來數小時的天氣與污染累積指數。
  • 依當日 PM2.5 對一個國家內的城市排名,可最髒或最乾淨優先。
  • 檢視單一感測器的品質評級與原因,並取得原始、5 分鐘、每小時或每日讀值。
  • 對最多 100 個感測器依 5 分鐘、小時或 UTC 日計算平均。
適用情境
適合助理回答某城市的空氣污染狀況、比較城市或國家、觀察長期趨勢,或用天氣解釋讀值。也適合在採信某個數值前先確認單一感測器的可靠度。
執行需求
可作為 api.atmy.ai 上的遠端端點以 streamable HTTP 使用,也可作為本機 npm 套件 atmy-mcp 以 stdio 執行。未宣告需要驗證、環境變數或標頭。
安裝前請注意
數值為近似值,彙整自公民、實驗性與政府感測器,並非官方監測。感測器讀值為裝置原始值,應搭配每個感測器的品質檢查與評級一起判讀。預報是天氣估計,不是 PM2.5 預報。伺服器要求在使用資料時標註 Atmy、城市頁面、天氣提供者,以及感測器網路及其授權。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Atmy air quality,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/ai.atmy%2Fair-quality/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "atmy-air-quality": {
      "type": "http",
      "url": "https://api.atmy.ai/mcp"
    }
  }
}

工具

11

search_cities

Search cities

Find the cities with an Atmy air-quality summary by name (any language) or country. Returns slugs to pass to the other tools.

輸入參數langlimitquerycountry

get_air_quality

Current air quality

PM2.5 now in a city (mean of the latest reading of each eligible sensor, at most 60 minutes old) with its US EPA category and the weather now (temperature, humidity, pressure, wind, clouds, precipitation), plus the last completed day from the Atmy Data Hub with its weather. Pass city or lat/lon.

輸入參數latloncitylangcountry

get_air_quality_history

Daily air quality history

Daily PM2.5 of a city from the Atmy Data Hub (UTC days, sensors after the quality check) with the day's weather from 2026-01-19 (mean, lowest and highest temperature, humidity, pressure, wind, strongest gust, clouds): the last days, or any period since 2017 with from/to, at most 400 days per call. For the whole history or records use get_air_quality_monthly first.

輸入參數tolatloncitydaysfromlangcountry

get_air_quality_monthly

Monthly air quality history

The whole measurement history of a city from the Atmy Data Hub: PM2.5 per month with the month's weather from 2026-01, yearly means (complete years marked), the dirtiest and cleanest months and days. For questions like "how has the air changed" or "the most polluted month on record".

輸入參數latloncitylangcountry

get_city_forecast

Weather and pollution accumulation forecast

The next hours of a city: temperature, wind, humidity, precipitation and the pollution accumulation index 0–100 (how strongly the weather keeps particles near the ground). A weather estimate, not a PM2.5 forecast.

輸入參數latloncitylanghourscountry

get_country_ranking

Country ranking

Cities of a country ranked by daily PM2.5 for the last completed day (Atmy Data Hub), most polluted or cleanest first.

輸入參數langlimitordercountry必填settlements

list_sensor_networks

Sensor networks

The sensor networks in Atmy (Sensor.Community, AirGradient, Atmy) with their number of sensors, how many pass the quality check, and their license.

無需輸入參數。

find_sensors

Find sensors

Single sensors with their latest reading (PM1, PM2.5, PM10, temperature, humidity, pressure), network and quality check: status, rating 0–10 of the last checked day, the mean rating of the last 7 days and the reasons. Filter by city, country, or a point with a radius; sort=rating puts the most reliable sensors first.

輸入參數latloncitypagesortlimitcountrynetworkqualityradius_kmmin_rating

get_sensor

One sensor

One sensor by its id: location, network, license, quality check with rating and reasons, and the latest reading.

輸入參數id必填

get_sensor_readings

Sensor readings

Readings of one sensor: raw (the last 31 days, at most 7 days a call), 5-minute means (the same windows), hourly means (the last 366 days, at most 92 days a call) or daily means (UTC days of the last 366 days, with the quality check of each day). Default: the last 24 hours, or 30 days by day. Times are UTC.

輸入參數id必填tofrominterval

get_sensors_average

Mean of a group of sensors

The mean of up to 100 sensors per 5 minutes, hour or UTC day, each sensor counted once per bucket, with the number of sensors in each bucket. Windows as in get_sensor_readings; by day at most 92 days a call.

輸入參數toids必填frominterval

版本歷史

3
  1. v1.1.0最新Oct 29, 2026
  2. v1.0.1Oct 23, 2026
  3. v1.0.0Oct 23, 2026

評分

已滿足適用檢查項的 75%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分

    請宣告包含 README 的 GitHub 儲存庫,或在 OAuth 受保護資源後設資料中提供 resource_documentation。

  • 授權條款10 分

    請在儲存庫或註冊中心條目中宣告授權條款。