DailyMeteo

io.github.srpp011由 GitHub 帳號 srpp011 發布v0.2.2更新於 Nov 3, 2026

Historical weather and climate normals for any land location, 1 km grids, 1961 to today

發布方自己的服務:daily.dev

概覽

AI 產生的概覽

DailyMeteo MCP 讓助理查詢全球陸地的歷史天氣與氣候常年值,資料來自 1 公里網格,涵蓋 1961 年至今。

可以做什麼
  • 把地名解析為經緯度與區域邊界
  • 取得某地點的日、月或年氣溫與降水數值,附摘要、年度彙總與 CSV 輸出
  • 比較 1961-1990 與 1991-2020 氣候常年值及其變化
  • 查看方案與剩餘額度,並訂購以電子郵件寄送的測站歷史 CSV 或區域 GeoTIFF 柵格
  • 列出並下載 Zenodo 上免費的 MeteoEurope1km 柵格檔案,含 MD5 驗證與續傳
  • 產生在 DailyMeteo 應用程式中開啟該地點與序列的連結
適用情境
適合回答某地歷史天氣、長期氣候趨勢或氣候變遷問題,或需要歐洲柵格氣候資料時。月值與年值、常年值以及 Zenodo 檔案不需帳號即可使用。
執行需求
以 Python 套件形式透過 uvx(Python 3.12)或 Docker 在本機執行,首次啟動約下載 60 MB。所有環境變數皆為選用:DAILYMETEO_EMAIL 與 DAILYMETEO_PASSWORD 用於帳號,或僅供日值使用的 DAILYMETEO_API_KEY,以及存放檔案的 DAILYMETEO_OUTPUT_DIR。地名查詢、資料取得與 Zenodo 下載需要網路。
安裝前請注意
日值會消耗額度(每天每變數 1 點),測站歷史消耗 1 個批次額度,區域下載會消耗 API 額度,應先估算並確認費用。超過 1,000 點的請求需明確確認。DAILYMETEO_PASSWORD 與 DAILYMETEO_API_KEY 是存放在用戶端設定中的密鑰。每年資料下載可達數 GB,且結果為插值網格而非測站實測。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 DailyMeteo,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。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

dailymeteo-mcp

An MCP server for DailyMeteo. With it, an AI assistant (Claude, VS Code, Cursor and other MCP clients) can answer questions about historical weather and climate change for any land location. Data are 1 km grids from 1961 to the present.

How much warmer are July days in Belgrade now than in 1961–1990? Which was the wettest year in Lisbon since 1961? Download daily mean temperature grids for Europe for 2003.

Install

Easiest: ask your AI assistant (Claude Code, Cursor, Cline…): "Install the DailyMeteo MCP server from github.com/srpp011/dailymeteo-mcp". It will follow llms-install.md.

Claude Code plugin. The plugin includes the server and a skill that tells Claude which tool to use. It asks for your DailyMeteo email and password, which are optional:

claude plugin marketplace add srpp011/dailymeteo-mcpclaude plugin install dailymeteo@dailymeteo

The first start downloads about 60 MB. If the server shows failed in a new session, wait a minute and reconnect it with /mcp.

All other clients need uv and run uvx --python 3.12 dailymeteo-mcp. See Configuration.

Tools

Everything the DailyMeteo app offers, for land areas worldwide, from 1961 to the present:

ToolWhat it doesCost
find_locationPlace name → latitude/longitude (OpenStreetMap)free
find_areaArea name → boundary polygon and size, for area downloadsfree
get_weatherDaily, monthly or annual values for a location; several variables at once; summary, yearly aggregates, trend, CSVmonthly/annual free; daily 1 credit per day and variable
get_climate_normalsNormals 1961–1990 and 1991–2020 and their change (year, months, or a calendar day)free
account_statusPlan, API credits, bulk creditsfree
request_point_historyEvery variable, daily, for one location (whole record by default), CSV by email1 bulk credit
estimate_area_downloadCost of daily rasters clipped to an area (max 3,000 km²)free
request_area_downloadDaily GeoTIFF rasters clipped to an area, by emailAPI credits
app_linkOpens the location and series in the DailyMeteo app (map, chart, CSV/PDF export)free
list_gridded_files / download_gridded_filesMeteoEurope1km raster archives on Zenodo (Europe, 1961–2020, incl. sea-level pressure)free

Variables are tmean, tmax and tmin in °C, and prcp in mm (monthly and annual values are totals).

As in the app, daily requests over 1,000 credits ask for the user's confirmation, and area downloads should be estimated before they are ordered. Repeating the same daily request is not charged again. Long series are not dumped into the conversation. They are summarised (per variable and per year) and saved as CSV.

Configuration

All environment variables are optional. Without any of them, monthly and annual values, normals, links and Zenodo grids work.

  • DAILYMETEO_EMAIL and DAILYMETEO_PASSWORD: your DailyMeteo account. They enable daily values, credits, point history and area downloads. Sign up at https://app.dailymeteo.com/.
  • DAILYMETEO_API_KEY: alternative for daily values only (Account → API Keys).
  • DAILYMETEO_OUTPUT_DIR: where CSV files and downloads are saved (default ~/dailymeteo).

Claude Code

claude mcp add dailymeteo -s user -e [email protected] -e DAILYMETEO_PASSWORD=... -- uvx --python 3.12 dailymeteo-mcp

Claude Desktop, Cursor, VS Code (mcpServers JSON)

json
{  "mcpServers": {    "dailymeteo": {      "command": "uvx",      "args": ["--python", "3.12", "dailymeteo-mcp"],      "env": { "DAILYMETEO_EMAIL": "[email protected]", "DAILYMETEO_PASSWORD": "..." }    }  }}

Docker (no local Python)

docker build -t dailymeteo-mcp .claude mcp add-json dailymeteo -s user '{"type":"stdio","command":"docker","args":["run","-i","--rm","-e","DAILYMETEO_EMAIL","-e","DAILYMETEO_PASSWORD","-v","/path/to/output:/data","dailymeteo-mcp"]}'

Data and citation

The values are interpolated grids, not station measurements. Results used in a publication should cite:

Sekulić, A., & Kilibarda, M. (2026). MeteoEurope1km (1961–2020): daily gridded meteorological dataset for Europe at a 1-km spatial resolution. Zenodo. https://doi.org/10.5281/zenodo.23264155

Built on the Python client dailymeteo. License: GPL-2.0-or-later.

來源:README.md,提交 26d0702

工具

11

find_location

Find a place

Latitude and longitude of a place (OpenStreetMap Nominatim). If several match, ask the user which one.

輸入參數limitquery必填

find_area

Find an area (polygon)

Boundary polygon (WKT) and size of a named area, for estimate_area_download / request_area_download.

輸入參數query必填

get_weather

Weather values for a location

Daily, monthly or annual values for one location and one or more variables, 1961 to the present. Monthly and annual values are free. Daily values cost 1 credit per day and variable and need an account or API key in the server configuration. Results include a summary per variable; series longer than 400 rows are not listed but summarised by year and saved as CSV.

輸入參數endlat必填lon必填datesstartsave_csvvariablestime_scaleconfirm_credits

get_climate_normals

Climate normals 1961-1990 vs 1991-2020

Climate normals for 1961-1990 and 1991-2020 and the change (newer minus older). Free. Without `month`, time_scale=mon returns all 12 months. Annual precipitation normals are yearly totals.

輸入參數daylat必填lon必填monthvariablestime_scale

account_status

DailyMeteo account and credits

Plan and remaining credits: API credits (daily point and area data) and bulk credits (point history).

無需輸入參數。

request_point_history

Order full point history (email)

Every variable, daily, for one location — by default the whole record since 1961 — as CSV by email. Costs one bulk credit (bulk credits are separate from API credits). Preparing the file takes minutes.

輸入參數endlat必填lon必填start

estimate_area_download

Estimate area download cost

Credit cost of daily rasters clipped to an area (max 3,000 km²), and the account balance.

輸入參數end必填bboxstart必填area_wktvariables必填

request_area_download

Order area download (email)

Daily GeoTIFF rasters clipped to an area (max 3,000 km²), prepared on the server and emailed. Spends API credits: run estimate_area_download first and get the user's agreement to the cost.

輸入參數end必填bboxstart必填area_wktvariables必填

list_gridded_files

List MeteoEurope1km grid archives

MeteoEurope1km archives on Zenodo (Europe, 1 km, 1961-2020, Cloud-Optimized GeoTIFF), free. Rasters are Equi7 Europe (EPSG:27704), Int16 in tenths of the unit (°C, mm, hPa), NoData -9999.

輸入參數yearsperiodproductvariable必填

download_gridded_files

Download MeteoEurope1km grid archives

Download MeteoEurope1km archives (1-3.5 GB per year of daily data), verify MD5, optionally unzip. Interrupted downloads resume. Tell the user the total size (list_gridded_files) before large downloads.

輸入參數unzipyearsperiodproductdest_dirvariable必填

版本歷史

1
  1. v0.2.2最新Oct 29, 2026

評分

已滿足適用檢查項的 90%

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25 分
  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

其他 Daily 整合