TrueFixR Storm Data API

io.github.truefixr由 GitHub 帳號 truefixr 發布v1.0.1更新於 Nov 6, 2026

Storm history by address since 2003, recent storm leads, model-based weather and storm forecasts.

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

遠端 MCP 伺服器,提供美國地址層級 2003 年以來的風暴歷史、近一年風暴線索、即時天氣與機器學習風暴預報,依次計費。

可以做什麼
  • 查詢單一房產自 2003 年以來的風暴歷史,含指定損失日期模式與可引用的參考編號
  • 取得單一地址或郡過去 365 天的近期風暴線索
  • 取得郡層級未來 24 小時至 10 天的風暴預報,含地址數量與預估成本
  • 取得座標或街道地址的即時天氣、生效的劇烈天氣警報及未來 48 小時逐時預報
  • 透過通用付費資料擷取工具存取更廣泛的資料集選單
適用情境
適合需要美國房產層級風暴紀錄、近期風暴活動或短期天氣與風暴預報的情境,例如保險、修復、物業管理或風險研究類問題。
執行需求
遠端 MCP 端點,無需本機安裝。資料擷取需付費:可透過 Authorization bearer 標頭使用預付 API 金鑰,或透過 x402 在 Base 上依次以 USDC 付款。未付款的請求會先回傳報價。
安裝前請注意
請求會產生費用:預報每地址 0.05 美元、歷史每筆事件 0.05 美元、天氣每次呼叫 0.0002 美元,limit 數值會放大帳單。通用工具屬於付費擷取,應優先使用專用工具。x402 代理可在無人確認下花費 USDC。預報與風暴紀錄並非損失評估或現場檢查,且提供者與 NOAA、NWS 無關。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 TrueFixR Storm Data API,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.truefixr%2Fatlascast-truefixr/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": {
    "truefixr-storm-data-api": {
      "type": "http",
      "url": "https://mcp.atlasunited.io/mcp"
    }
  }
}

README

Atlas United storm data API: ML forecasts and storm history for every U.S. address

Atlas United builds risk models for every U.S. address (latitude/longitude), with all the information inside each location. This repository documents the API: address-level storm forecasts for the next 24 hours to 10 days, plus every reported storm at that address back to 2003. Pay per address, no contract.

AtlasCast is Atlas United's forecasting model suite: probabilistic, address-level forecasts for 10 perils, refreshed 4 times a day. TrueFixR is the storm-data side: reported and radar-detected storm history by address. Not affiliated with NOAA or the NWS.

The five products

#Productdataset=Price
1ML Storm Forecast by Addressrisk$0.05 per address
2Model-Based Weather by Addressweather$0.0002 per call
3Model-Based Hourly Forecast by Addressweather with hours_ahead (0 to 48)$0.0002 per call
4Storm History by Address: Reported and Radar-Detected Events Since 2003history$0.05 per event line, no minimum
5Past Storm Leads by Address: Reported and Radar-Detected, Last 365 Daysstorms$0.05 per address

Products 1 to 3 are model outputs. Products 4 and 5 are recorded events matched to addresses.

1. ML Storm Forecast by Address

Probabilistic, address-level forecasts for 10 perils (tornado, hail, wind, flash flood, heavy rain, winter, ice, coastal surge, hurricane and wildfire), 24 hours to 10 days ahead, refreshed 4 times a day. AtlasCast uses a separate machine-learning model for each peril. Models are trained and validated chronologically on held-out reported events, and inputs are restricted to information available at forecast issue time.

Each address record carries the structure replacement value and the estimated people at that address, plus storm type, forecast time, a risk label and a past-hit count. Replacement value is the cost to rebuild the structure, not market value. Windows: 24h, 48h, 3d, 5d, 7d, 10d. Filter by county, peril and window. Without payment you get the address count and exact price first; county grade and per-peril totals are a County Summary ($0.02 per county). Forecasts describe what could happen, not what will happen.

2. Model-Based Weather by Address

Point weather for any U.S. coordinate: current conditions, active severe weather alerts and a short-term rain outlook. $0.0002 per call. Add details=true for the full pull of over 170 variables at $0.0002 per call.

3. Model-Based Hourly Forecast by Address

Add hours_ahead (0 to 48) to the weather dataset for forecast hours instead of current conditions. The response reports the hour actually used in forecast_hour_used. Forecast hours carry a smaller core set of fields. $0.0002 per call.

4. Storm History by Address: Reported and Radar-Detected Events Since 2003

One property's long record: every storm event reported or radar-detected within a chosen radius, 2003 to the present, across 11 categories (hail, wind, flood, lightning, tornado, hurricane, winter storm, extreme heat and cold, drought, wildfire, coastal). Each line has event date, type, magnitude where measured, distance in miles and county. Citable, with a reference_id. An optional date_of_loss mode shows whether an event was reported or radar-detected near the address on a date, and lists events before and after it. A record of reported and radar-detected events, not a damage assessment.

5. Past Storm Leads by Address: Reported and Radar-Detected, Last 365 Days

Address-level records of storm events reported or radar-detected at or near each address over the trailing 365 days, filterable by county, peril and severity. Each record has the event time (UTC), type, measured or radar-estimated severity with its unit, distance and a repeat-hit count. Without payment you get the address count and exact price first. Not a damage assessment.

Access

MethodBest for
REST APIPrepaid API key (top up from $1), Authorization: Bearer <key>
MCP serverClaude, ChatGPT and other MCP-compatible AI clients
x402Autonomous AI agents: pay per request in USDC on Base, no account

Same prices either way. Every request without payment returns the exact price first (HTTP 402 quote with the count, the price and a card pay link). Every paid response carries a reference_id receipt, and an identical paid query within 24 hours is not billed twice.

Endpoint

GET  https://data.truefixr.com/v1/dataPOST https://data.truefixr.com/v1/data   (same params as a JSON body, keeps addresses out of URLs)
ParamDescription
datasetrisk, weather, history, storms, plus address, hazard_score, facilities, wildfire (county-level), at_risk, daily, coverage
state / county2-letter state code / county name
perilNarrow by peril, for example HAIL, FLASH_FLOOD, HEAVY_RAIN, TORNADO
windowrisk only: 24h, 48h, 3d, 5d, 7d, 10d
hours_aheadweather only: 0 to 48
addressesOmit for the price quote (HTTP 402). true for the paid pull (weather uses details=true)
limitMax records returned (limit=10 on a $0.05 dataset is a 50 cent sample)
formatjson or csv

Call the endpoint with no params for the live machine-readable menu. Full detail per dataset: Datasets.

Batch endpoints

EndpointMax locationsPrice
POST /v1/weather/batch500$0.0002 per location
POST /v1/portfolio/risk500$0.05 per location (county forecast status, not address-level)

For AI agents

An agent with no API key and no human in the loop can pay per call with x402:

  1. Request a paid pull, for example GET https://data.truefixr.com/v1/data?dataset=storms&county=Dallas&state=TX&addresses=true&limit=1.
  2. Receive HTTP 402 with the exact price.
  3. Sign a USDC payment on Base (eip155:8453) and retry with the payment header.
  4. Receive the data. No signup, no key.

Manifest: /.well-known/x402.json. Agent docs: llms.txt.

Data honesty

  • Forecasts describe what could happen, not what will happen.
  • A storm reported or radar-detected near an address is not a property inspection, damage assessment or repair estimate.
  • structure_value is replacement cost (what it costs to rebuild), not market value.
  • Not affiliated with NOAA or the NWS.

Who this is for

Insurers, adjusters, emergency management, property managers, restoration, solar, and data and AI-agent builders.

Documentation

Links

來源:README.md,提交 133b86c

工具

6

get_weather_data

Atlas United data, all datasets (advanced / multi-county)

CATCH-ALL and PAID-PULL tool. Prefer the dedicated tools below when one fits (get_storm_history: one county, past 365 days; get_risk_forecast: one county, next 24 hours to 10 days; get_address_report: one address, past 365 days; get_property_storm_history_report: one address, 2003 to present; get_current_weather: one point, now to 48 hours). Use THIS tool for: every PAID address-level pull (set addresses=true), county coverage, facilities, wildfire (county-level), at_risk, daily, a counties multi-county rollup (comma-separated, max 15), hazard_score, or any parameter the dedicated tools do not expose (radius_mi, date_of_loss, window, months, category, limit, kind, details, hours_ahead). Datasets: ML Storm Forecast by Address (risk), Model-Based Weather by Address (weather), Model-Based Hourly Forecast by Address (weather with hours_ahead), Storm History by Address: Reported and Radar-Detected Events Since 2003 (history), Past Storm Leads by Address: Reported and Radar-Detected, Last 365 Days (storms). addresses=false (default) is a FREE preview; addresses=true (or details=true for weather) returns the paid data and requires the user's own Atlas United Data API account key, or an x402 payment. Call with no arguments for the full menu. HARD RULE when called with no arguments: this returns the full menu. Output that entire raw response back to the user verbatim, every dataset, every field, every example. Do not summarize or paraphrase. A shortened version is wrong even if it looks complete.

輸入參數latlondayskindlimitperilstatecountyformatmonthswindowaddress另有 11 個

get_storm_history

Past Storm Leads by Address (county preview)

COUNTY LEVEL, FREE, PAST 365 DAYS. Past Storm Leads by Address: Reported and Radar-Detected, Last 365 Days. Use when the question is how much storm activity a county has had in the past year: event counts, storm types, measured severity ranges and repeat properties. Input is state plus county, never a street address. Not for one property (use get_address_report), not for the 2003-to-present record (use get_property_storm_history_report), not for future storms (use get_risk_forecast). Not a damage assessment. For the paid address-level list, call get_weather_data with dataset=storms and addresses=true ($0.05 per address; needs an Atlas United Data API key or an x402 payment).

輸入參數daysperilstate必填county必填min_severity

get_risk_forecast

ML Storm Forecast by Address

COUNTY LEVEL, FREE, FUTURE (next 24 hours to 10 days). ML Storm Forecast by Address. Use when the question is which storms could affect a county soon: counts of addresses in the forecast path, the storm types forecast and the estimated cost (the county's A-F grade is shown as a secondary label). Input is state plus county. Per-peril machine-learning models, refreshed 4 times a day. Could happen, not will. Not for past storms (use get_storm_history, get_address_report or get_property_storm_history_report) and not for current weather (use get_current_weather). The paid pull (addresses=true, $0.05 per address) returns one record per address with structure_value (USD replacement cost), people (estimated occupants), full_address, lat, lon, county, storm_type, forecast_time and risk_label. For the paid pull, call get_weather_data with dataset=risk and addresses=true (needs an Atlas United Data API key or an x402 payment).

輸入參數perilstate必填county必填window

get_property_storm_history_report

Storm History by Address: Reported and Radar-Detected Events Since 2003

ONE PROPERTY, 2003 TO PRESENT. Storm History by Address: Reported and Radar-Detected Events Since 2003. Use when the user wants the full citable record for a single address, or a date-of-loss lookup: 11 event categories (hail, wind, flood, lightning, tornado, hurricane, winter storm, extreme heat/cold, drought, wildfire, coastal) in one report. Input is a street address or lat/lon. Not the 365-day snapshot (use get_address_report) and not a county summary (use get_storm_history). Free preview shows the report-line count and exact price before anything is paid. Paid report: $0.05 per line, $10.00 minimum per report. Optional date_of_loss anchors the report around one date and lists the events reported or radar-detected on and around it, for reference; it is not a determination of whether any claim is valid. Address and date of loss are sent in a POST body, which keeps them out of URLs and logs.

輸入參數latlonaddressaddressesradius_mix_paymentdate_of_loss

get_current_weather

Model-Based Weather by Address (hourly forecast with hours_ahead)

ONE POINT, NOW TO 48 HOURS. Model-Based Weather by Address: point weather for any U.S. coordinate or street address, with current conditions, active severe weather alerts and a short-term rain outlook. Use for what the weather is or will be at a location; add hours_ahead=0-48 for Model-Based Hourly Forecast by Address. Not for storm history or storm-risk forecasts (use get_address_report, get_property_storm_history_report, get_storm_history or get_risk_forecast). FREE by default: the lean response needs no account. details=true returns the full pull, billed $0.0002 per call (not per address).

輸入參數latlonaddressdetailsx_paymenthours_ahead

get_address_report

Property Snapshot by Address (365-day past storm leads plus county forecast label)

ONE PROPERTY, PAST 365 DAYS. Property Snapshot by Address: Past Storm Leads plus County Forecast Label. Use for recent storms at one exact address: its own reported and radar-detected storm events within a tight radius (about 150 m), with the county's current forecast label as secondary context. Input is an address with county and state, or lat/lon. Not the full archive (use get_property_storm_history_report, Storm History by Address, which searches a wider 5-mile radius so counts will differ), not a county summary (use get_storm_history), and not forecasts (use get_risk_forecast, ML Storm Forecast by Address). For paid single-address data, call get_weather_data with dataset=address and addresses=true ($0.05 flat per address; needs an Atlas United Data API key or an x402 payment).

輸入參數latlonstatecountyaddress

版本歷史

2
  1. v1.0.1最新Oct 9, 2026
  2. v1.0.0Sep 25, 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