open-signals

io.github.Civops-Platform由 GitHub 帳號 Civops-Platform 發布v0.1.0更新於 Oct 24, 2026

Public hazard, water, weather and EPA data with source, age and licence on every reading.

發布方自己的服務:SIGNALS Loyalty Agent Platform

已驗證Streamable HTTP可網頁執行位置與生活網頁搜尋與抓取資料與分析

概覽

AI 產生的概覽

遠端 MCP 伺服器,提供公共災害、水文、天氣與 EPA 資料源目錄,回傳附來源、時間與授權的讀值與 GeoJSON 圖層。

可以做什麼
  • 搜尋並檢視公共資料源目錄、相關專案彙整與具名地點
  • 從單一資料源取得目前讀值,含數值、單位、地點與來源資訊
  • 列出地圖圖層,並依日期取得某一圖層的 GeoJSON 要素集合
  • 列出靜態公共 GeoJSON 資料集,並取得某一分片的網址
  • 區分實測、模型推算與衍生讀值
適用情境
適合需要權威公共資料做地圖、監測或研究的場合,例如地震、洪水、水位、天氣、空氣品質、火災、船舶、飛機、能源與申報資料,並要求每個數字都標明來源與授權。也可在撰寫抓取程式前用來尋找合適的公共 API。
執行需求
無需安裝:遠端 streamable HTTP 端點,無狀態且不需驗證,公共實例依 IP 限流。自行部署需 Node 20 以上版本;部分資料源需要免費金鑰,例如 NASS_API_KEY 或 EBIRD_API_KEY。
安裝前請注意
所有工具皆為唯讀,但資料依上游原樣轉送,可能延遲、為初步值、被修訂或本身有誤;專案聲明不適用於導航、安全或無法容忍錯誤讀值的決策。非商業、受限或未審核授權的資料源會被公共伺服器拒絕,授權條款隨每筆讀值一併傳遞。i3X 端點使用一個公開的唯讀權杖。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 open-signals,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/io.github.Civops-Platform%2Fopen-signals/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": {
    "open-signals": {
      "type": "http",
      "url": "https://open-signals.civops.io/mcp"
    }
  }
}

README

open-signals

Public data, ready for maps and agents. Every reading says where it came from, when it was fetched, and what licence it carries.

open-signals has three parts:

  • A catalogue of public data sources (catalog/sources.json). Each entry gives the API, coverage, cadence, the key it needs and its licence. Weather, water, ice, hazards, flights, ships, satellites, energy, emissions, filings, trade and more. It's the list to check before writing yet another fetcher.

  • Fetchers for the sources we read today. Each one turns an upstream answer into one shape, the reading:

    json
    { "id": "noaa-coops:9063085:2026-10-10", "at": "2026-10-10", "metric": "water_level",  "value": 2.762, "unit": "ft above LWD",  "summary": "Lake Erie at Toledo 2026-10-10: mean 2.76 ft above low water datum (…)",  "place": { "id": "coops-toledo", "name": "Lake Erie at Toledo", "lat": 41.6936, "lng": -83.4723 },  "fields": { "station": "9063085", "datum": "LWD", "readings": 155 },  "source": { "id": "noaa-coops", "name": "NOAA CO-OPS water levels", "url": "https://tidesandcurrents.noaa.gov/…",              "fetched_at": "2026-10-10T19:12:03Z", "license": "public_domain" } }
  • Ways in: a CLI, a REST API with an OpenAPI description, an MCP server for agents, and GeoJSON map layers. There are no runtime dependencies; it needs Node 20 or later.

Use it

A public instance runs at https://open-signals.civops.io (REST under /v1, MCP at /mcp). It serves only public-domain and open sources, holds no upstream keys, and is rate-limited per IP. Try https://open-signals.civops.io/v1/layers/volcanoes?elevated=true.

bash
git clone https://github.com/Civops-Platform/open-signals && cd open-signals   # Node 20+, no npm install neededalias open-signals='node bin/open-signals.mjs'open-signals sources fires                     # search the catalogueopen-signals sources --topic water --fetchableopen-signals fetch usgs-earthquakes --min 4.5 --window weekopen-signals fetch noaa-coops --coops 8518750   # any CO-OPS stationopen-signals fetch open-meteo --lat 41.5 --lng -81.7open-signals layer water_level                 # GeoJSONopen-signals serve --port 3290                 # REST + MCP

fetch and layer run on your machine with your own keys (NASS_API_KEY, EBIRD_API_KEY). The CLI prints each source's licence so you know what you may do with what you fetched.

REST

GET /v1/sources?query=&topic=&license=&fetchable=search the catalogue
GET /v1/sources/{id}one entry
GET /v1/hubsprojects that collect sources (below)
GET /v1/places?tag=named places as GeoJSON
GET /v1/readings?source={id}&place=&tag=&lat=&lng=&coops=&usgs=&ebird=&state=&bbox=&metric=&since=&limit=readings
GET /v1/layers · GET /v1/layers/{id}?date=map layers as GeoJSON
GET /openapi.jsonthe full description

CESMII i3X

The same layers are served as a read-only CESMII i3X 1.0 endpoint at https://open-signals.civops.io/i3x/v1. The address space has a root, one folder per layer, and one object per place or event. Each object's value is its latest reading (value, quality, timestamp) with source and licence, and its history is every reading held for that place. Subscriptions support sync and server-sent-event streams.

CESMII's conformance suite (build 6, run 10 October 2026) rates it i3X 1.0 Compatible: 50 passed, 0 failed, 10 skipped (report). The skipped tests are the write tests; full compliance needs writes, and a server that republishes public data has nothing to write.

The spec requires authentication on data endpoints, so there is a free public read-only token: os-public-read (send Authorization: Bearer os-public-read). GET /i3x/v1/info needs none.

Static datasets

Data that changes slowly is served as GeoJSON files rather than fetched live: wildfire burn perimeters for the last 20 years (NIFC WFIGS and USFS MTBS, one file per state), public-land share by county (USGS PAD-US 4.1), federal campgrounds (RIDB) and fire-weather stations (RAWS), all public domain. GET /v1/datasets lists them with source, licence and parts; GET /v1/datasets/{id}/{part} returns one part (a two-letter state, or all). A deployment points OPEN_SIGNALS_DATA_DIR at a folder holding the files and an index.json; the format is described in src/datasets.js.

MCP

POST /mcp uses the streamable HTTP transport (JSON-RPC 2.0). It is stateless and needs no auth. Every tool is read-only:

  • search_sources, get_source, list_hubs, list_places
  • get_readings, list_layers, get_layer
  • list_datasets, get_dataset_part

To add it to a client:

json
{ "mcpServers": { "open-signals": { "type": "http", "url": "https://open-signals.civops.io/mcp" } } }

Licences: what a server will republish

The code is Apache-2.0. The data is not ours to relicense. Every source keeps its own terms, and the licence travels on every reading. A running server republishes data, so it applies a gate:

licenceexamplesserved
public_domainNOAA, USGS, USDA, NASA FIRMS, SECalways
openCC BY, ODbL (OpenStreetMap, adsb.lol, ECMWF, GDELT)always; attribution travels with it
non_commercialOpen-Meteo free tier, eBird, OpenSkyonly with OPEN_SIGNALS_NONCOMMERCIAL=1 (you run a non-commercial deployment)
restrictedGoogle 3D Tiles, TomTomnever
unknownanything not yet reviewednever

A refused source answers 451 with the licence and the reason. Fetching for yourself with the CLI is not republishing, so the gate doesn't apply there.

Fetchers today

sourcewhatkey
usgs-earthquakesworldwide earthquakes, by window and magnitude floor—
usgs-volcanoesalert level and aviation colour code for every monitored US volcano—
noaa-nwpsriver stage and flood category (observed and forecast) at every NOAA gauge in a box—
epa-echomajor EPA-regulated facilities in a state, with compliance status and penalties—
openfda-recallsFDA food, drug and device recalls of the last 60 days, at the firm's ZIP—
usaspendingthe 100 largest new federal contract awards of the last 30 days, at the place-of-performance ZIP—
gbifopen-licensed (CC0, CC-BY) wildlife and plant observations of the last two weeks, worldwide, by group and box—
nasa-eonetopen natural events worldwide (storms, wildfires, volcanoes, floods, ice), latest position—
world-bankWorld Bank indicators by country at the capital: GDP growth, inflation, manufacturing, exports, FDI, unemployment—
emscEMSC-CSEM earthquakes worldwide, densest over Europe (CC BY 4.0), by window and magnitude floor—
noaa-ibtracsthe latest best-track fix of every active tropical cyclone, any basin—
eurostatindustrial production by country (index or year-on-year), latest month, at the capital—
gem-trackersGlobal Energy Monitor Global Integrated Power Tracker (CC BY 4.0, 2026-08 release): plants of 50 MW and up, operating or under construction, by country, fuel and status (replaces the WRI database, static since 2021)—
openfemaFEMA disaster declarations of the last 90 days, at the county (or state) point—
usda-ams-bargeweekly downbound grain tonnage at seven Mississippi, Illinois, Ohio and Arkansas River locks (USDA AMS, from USACE LPMS)—
bts-border-crossingsinbound trucks, trains and vehicles per US-Canada and US-Mexico port of entry, latest month—
epa-triToxics Release Inventory: on-site releases per facility in a state, latest reporting year—
epa-campdpower-plant CO2, SO2 and NOx per facility in a state, latest month in EPA's keyless bulk files—
noaa-coopswater levels at any CO-OPS station (LWD on the Great Lakes, MLLW on tidal stations)—
usgs-waterriver discharge and gage height at any USGS gauge—
glerlGreat Lakes ice cover (December to May)—
usda-nassweekly crop progress and condition, national and by stateNASS_API_KEY (free)
open-meteodaily weather, 92 days back and 7 forward, anywhere— (non-commercial)
waterfowl-wsithe duck Weather Severity Index (Schummer et al. 2010) from Open-Meteo— (non-commercial)
ebirdwaterfowl reported in an eBird region in the last 7 daysEBIRD_API_KEY (free, non-commercial)
open-meteo-floodGloFAS river discharge today at about a hundred large-river locations worldwide, with the week's change and the 30-day ensemble high— (non-commercial)
open-meteo-airCAMS modelled air quality now at 150 large cities: US AQI, European AQI, PM2.5, PM10— (non-commercial)
adsb-lollive aircraft from the adsb.lol receiver network (ODbL): around any point (mode=area), every military-flagged aircraft worldwide (mode=military), or GPS interference per 1° cell inferred from aircraft position accuracy (mode=gps, the GPSJam method). Aircraft in the FAA LADD and PIA privacy programmes are never served—
nasa-firmsNASA FIRMS VIIRS heat detections from the keyless global files: fires of the last 24 hours (mode=fires), ~1 km spots hot on 3+ of the last seven days (mode=persistent, derived: industry, flares, volcanoes), and heat days with owner and parent company at every hot site in four Global Energy Monitor trackers: blast-furnace and DRI steel plants (mode=steel), cement kilns (mode=cement), chemical plants (mode=chemicals) and oil and gas fields (mode=oil_gas, flaring), all derived—
nws-alertsactive National Weather Service watches, warnings and advisories, one point per alert per county; by state, kind or event—
usbr-riseBureau of Reclamation daily storage at about 215 western reservoirs (RISE), with the week's change; by Reclamation region—
digitraffic-aislive ship positions in Finnish waters and the northern Baltic (Fintraffic, CC BY 4.0), with name, type and destination; pleasure craft never served—
corroborationderived: the same event seen by two independent sources or one. Earthquakes in USGS and EMSC (a relayed USGS-network solution counts once), and US wildfire incidents against FIRMS satellite heat—
smithsonian-gvpSmithsonian Volcanoes of the World: volcanoes erupting since 1900 worldwide, and those erupting now— (non-commercial)

Observed, modelled or derived

A sensor reading and a conclusion drawn from it are not the same thing, so a reading says which it is. No basis means something observed it (a gauge, a seismometer, a receiver). basis: "modelled" is a model's output (Open-Meteo weather, GloFAS discharge, CAMS air quality). basis: "derived" is inferred from other readings and carries derived_from saying from what (GPS interference from aircraft NACp, the duck Weather Severity Index from modelled weather, persistent heat and steel-plant heat from FIRMS detections, and corroboration, which pairs two sources on one event and says when an apparent second source is only relaying the first). Layer features always carry basis.

The rest of the catalogue is listed but not fetched yet. Adding a fetcher is the most useful contribution; see CONTRIBUTING.md.

Hubs

catalog/hubs.json lists the projects we watch so we don't search from scratch each time:

  • God's Eye View (Bilawal Sidhu and Sameh Khamis)
  • World Monitor
  • OSIRIS and WorldWideView
  • Shadowbroker, ULTOR and Gemini / Claude Earth (community builds on the God's Eye View recipe)
  • the official MCP Registry and awesome-mcp-servers
  • Source Cooperative, the AWS Open Data registry, Data.gov and public-apis

When a source is found through one of them, its entry records that in found_via.

Run it

bash
npm test                  # offline, upstreams stubbednpm run test:live         # every fetcher against its real upstream, then REST and MCPPORT=3290 npm start
variablemeaning
PORTdefault 3290
OPEN_SIGNALS_NONCOMMERCIAL=1this deployment is non-commercial and may republish non-commercial sources
RATE_LIMIT_PER_MINper client IP, default 60
TRUST_PROXY=1read the client IP from X-Forwarded-For behind a proxy

Responses are cached in memory per source, place and parameters (2 minutes for earthquakes, up to 6 hours for weekly sources), so upstreams see polite traffic.

No warranty

open-signals passes on what public agencies and projects publish, as they publish it. Readings can be late, preliminary, revised or wrong upstream. It is provided as is (see LICENSE), and it is not for navigation, safety or any decision that cannot tolerate a bad reading.

來源:README.md,提交 7e285f9

工具

9

search_sources

Search the catalogue of public data sources (weather, water, hazards, flights, ships, energy, filings, trade, ...). Each entry gives the API, coverage, cadence, auth needed and licence. Use it to find where a kind of data comes from before writing a fetcher.

輸入參數querytopiclicensefetchable

get_source

One catalogue entry in full.

輸入參數id必填

list_hubs

Projects and catalogues that collect sources (God's Eye View, World Monitor, the MCP Registry, Source Cooperative, ...), with how each relates to this one.

無需輸入參數。

list_places

Named places the fetchers read for, with their upstream ids (CO-OPS station, USGS gauge, eBird region) and tags.

輸入參數tag

get_readings

Fetch current readings from one source, each with value, unit, a one-line summary, place and provenance (source, URL, fetch time, licence). Sources this server will not republish (non-commercial, restricted or unreviewed licence) answer with an error naming the licence.

輸入參數latlngmintagbboxusgscoopsebirdlimitplacesincestate另有 5 個

list_datasets

Static public datasets this server holds as GeoJSON (wildfire burn perimeters, public-land share by county, federal campgrounds, fire-weather stations), with source, licence, feature count and parts (one per state, or "all").

無需輸入參數。

get_dataset_part

The URL of one part of a dataset as GeoJSON, plus its description. Fetch the URL for the features; parts can be several megabytes.

輸入參數id必填part必填

list_layers

Map layers this server can draw as GeoJSON, with unit, source, licence, whether it is available here, and how to read it.

無需輸入參數。

get_layer

One map layer as a GeoJSON FeatureCollection: one point per place with the reading on the date (else the latest observed before it, never a guess), or one point per event for event layers.

輸入參數id必填latlngmintagbboxdatefuelusgscoopsebirdplace另有 9 個

版本歷史

1
  1. v0.1.0最新Oct 10, 2026

評分

已滿足適用檢查項的 100%

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
  • 授權條款10 分

其他 Signals 整合