原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Noaa Cdo MCP Server

作者:cyanheads版本 0.1.15i★ –i电脑或云端
注册名称io.github.cyanheads/noaa-cdo-mcp-server

安装

概览

作者提供的说明(英文原文)

Search NOAA CDO stations and datasets, fetch historical weather observations.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

  • 连接方式: 电脑或云端
  • 传输方式: stdio, Streamable HTTP
  • 分类: 搜索与 AI 记忆
  • 你需要填写:NOAA_CDO_TOKEN

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

  • 基础检查:1 项中通过 1 项
  • 在作者的服务器上运行:你向它提出的内容会经过他们的服务器。
  • 需要你自己填写: NOAA_CDO_TOKEN, MCP_LOG_LEVEL

你需要

  • 在云端运行无需安装任何东西,通过互联网连接
  • npm已安装 Node.js(用于 npx 命令)

你用的是哪个应用?

在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。

适用于网页版、桌面版和手机版 Claude:

  1. 打开 Settings → Connectors
  2. 点击 Add custom connector
  3. 粘贴下面的地址,然后点击 Add
  4. 如果要求登录,请登录作者的服务
SettingsConnectors1+ Add2https://…3
https://noaa-cdo.caseyjhand.com/mcp

或者在你的电脑上运行

打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "noaa-cdo": {
      "command": "npx",
      "args": [
        "-y",
        "@cyanheads/noaa-cdo-mcp-server",
        "run",
        "start:stdio"
      ],
      "env": {
        "NOAA_CDO_TOKEN": "your-value",
        "MCP_LOG_LEVEL": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add --transport http noaa-cdo https://noaa-cdo.caseyjhand.com/mcp

或者在你的电脑上运行

claude mcp add noaa-cdo --env NOAA_CDO_TOKEN=your-value --env MCP_LOG_LEVEL=your-value -- npx -y @cyanheads/noaa-cdo-mcp-server run start:stdio

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "noaa-cdo": {
      "url": "https://noaa-cdo.caseyjhand.com/mcp"
    }
  }
}

或者在你的电脑上运行

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "noaa-cdo": {
      "command": "npx",
      "args": [
        "-y",
        "@cyanheads/noaa-cdo-mcp-server",
        "run",
        "start:stdio"
      ],
      "env": {
        "NOAA_CDO_TOKEN": "your-value",
        "MCP_LOG_LEVEL": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "noaa-cdo": {
      "type": "http",
      "url": "https://noaa-cdo.caseyjhand.com/mcp"
    }
  }
}

或者在你的电脑上运行

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "noaa-cdo": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@cyanheads/noaa-cdo-mcp-server",
        "run",
        "start:stdio"
      ],
      "env": {
        "NOAA_CDO_TOKEN": "your-value",
        "MCP_LOG_LEVEL": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

ChatGPT 只能连接互联网上的服务器:

  1. 打开网页版 ChatGPT → Settings → Connectors (Apps)
  2. 点击 Create 或 Add(部分套餐需要先在 Advanced 中开启 Developer mode)
  3. 粘贴下面的地址,起个名字,然后保存
  4. 如果要求登录,请登录作者的服务
SettingsConnectors1+ Create2https://…3
https://noaa-cdo.caseyjhand.com/mcp

菜单名称可能因套餐和版本不同而略有差异。

你的选择通过 Cookie 保存在这台设备上,无需账户。

需要你填写的值

  • NOAA_CDO_TOKEN 必填 env
    NOAA CDO API token. Obtain free at https://www.ncdc.noaa.gov/cdo-web/token.
  • MCP_LOG_LEVEL env
    Sets the minimum log level for output (e.g., 'debug', 'info', 'warn').

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

它能做什么

我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 cyanheads 验证,该账户拥有此仓库

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    端点有响应

    尚未检查;我们会轮流检查各个端点

  • … 尚未检查

    使用 OAuth 登录

    尚未检查;我们会轮流检查各个端点

  • … 尚未检查

    工具描述中没有隐藏指令

    尚未检查;我们会在检查端点时读取工具列表

与“搜索与 AI 记忆”中的其他服务器比较i

  • 星标数多于此分类中其他 7275 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 7275 个服务器的 17% 更新
  • 基础检查结果等于或优于此分类中其他 7275 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

Noaa Cdo MCP Server 安全吗?

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

你需要填写:NOAA_CDO_TOKEN

它在我的电脑上运行还是在云端?

两种方式都可以:安装在你的电脑上,或者连接云端版本。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(0.1.15)于5个月前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。

有什么可以替代它?

同一分类中有:Context7, Codebase Memory, Exa

替代选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Context7

作者:upstash

Up-to-date docs for AI agents

电脑或云端★ 64,224MIT昨天更新
安装

Codebase Memory

作者:DeusData

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

在你的电脑上运行★ 48,148MIT21天前更新
安装

Exa

作者:exa-labs

Connect AI agents to Exa for web search, content fetching, and multi-step research.

在云端运行★ 5,213MIT上个月更新
安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

@cyanheads/noaa-climate-mcp-server Search NOAA climate stations and datasets, fetch historical weather observations via MCP. STDIO or Streamable HTTP. 10 Tools • 2 Data Resources • 1 Skill

Public Hosted Server: https://noaa-climate.caseyjhand.com/mcp


Overview

Historical weather and climate records from NOAA: station observations from Climate Data Online, the Storm Events Database, and Billion-Dollar Weather and Climate Disasters. Find stations, pull observations in the units you want, and look up storm damage or disaster costs.

Tools
ToolDescription
noaa_climate_list_datasetsList available CDO datasets with IDs, names, and temporal coverage
noaa_climate_list_data_categoriesList data category groups (Temperature, Precipitation, Wind, etc.)
noaa_climate_list_data_typesList specific measurement labels (TMAX, TMIN, PRCP, SNOW, etc.) by dataset or category
noaa_climate_list_location_categoriesList the 12 location categories that scope location search
noaa_climate_find_locationsSearch geographic locations by category (states, cities, counties, zip codes, climate regions), with an optional name filter
noaa_climate_find_stationsSearch weather stations by location, bounding box, dataset, and data type
noaa_climate_get_stationFetch full metadata for a single station by ID
noaa_climate_fetch_dataFetch historical observation records for a dataset and date range
noaa_climate_search_storm_eventsSearch the NCEI Storm Events Database for one year — tornadoes, hail, floods, hurricanes, with damage, casualties, and narratives
noaa_climate_get_billion_dollar_disastersQuery NOAA's retired 1980–2024 Billion-Dollar Weather and Climate Disasters archive — CPI-adjusted costs and deaths per disaster, or per-year totals by disaster class
Resources
ResourceDescription
noaa://datasetsAll CDO datasets with IDs and temporal coverage — injectable context for orienting an agent before querying data
noaa://stations/{stationId}Station metadata by ID — name, coordinates, elevation, and data coverage date range
Agent skill

noaa-climate-guide covers historical comparisons, coverage checks, observation quality, and storm-to-station investigation. It ships with plugin, npm, Docker, and MCPB installs and is served through the MCP Skills extension and a skill resource alongside the two data resources.

Capability reference

Every stationId input, including the station resource, trims surrounding whitespace and uppercases IDs. Bare 11-character GHCN IDs (USW00024233) become GHCND:USW00024233. Namespaced IDs such as COOP:454769, NEXRAD:KATX, and unfamiliar nonempty namespace/payload pairs remain accepted; ambiguous bare IDs are rejected. Tools disclose changes in a notice; the resource returns the canonical station ID. Syntax does not establish that a station exists.

noaa_climate_list_datasets tool
  • No required inputs; optional data type, location, station, and date-range filters; limit 1–1000 (default 25) with offset, sortable by id, name, mindate, maxdate, or datacoverage
  • Returns each dataset's ID, name, and date span — GHCND (daily, 1763–present), GSOM (monthly), GSOY (annual), NORMAL_DLY/MLY/ANN/HLY (1981–2010 normals)
  • Date filters use inclusive coverage overlap: maxdate >= startDate and mindate <= endDate for each supplied bound. The complete catalog matching the other filters is retrieved before filtering and pagination; totals describe that filtered view.

noaa_climate_list_data_categories tool
  • Optional dataset, location, station, and date-range filters; limit 1–1000 (default 25) with offset, sortable by id or name
  • Returns the 42 measurement categories (Temperature, Precipitation, Wind, Pressure, Sunshine, and more), whose IDs narrow noaa_climate_list_data_types as datacategoryId

noaa_climate_list_data_types tool
  • Filter by datasetId (e.g. GHCND) or datacategoryId (e.g. TEMP); limit 1–1000 (default 25) with offset
  • Returns the datatype IDs noaa_climate_fetch_data takes — common GHCND types are TMAX, TMIN, PRCP, SNOW, SNWD, AWND — with coverage and date range when CDO carries them

noaa_climate_list_location_categories tool
  • Pagination and sort only: limit 1–1000 (default 25) with offset, sortable by id or name
  • Returns the 12 category IDs noaa_climate_find_locations accepts as locationCategoryId: CITY, ST, CNTY, CNTRY, ZIP, US_TERR, CLIM_REG, CLIM_DIV, HYD_ACC, HYD_CAT, HYD_REG, HYD_SUB

noaa_climate_find_locations tool
  • locationCategoryId scopes the search (e.g. ST returns all 51 states); optional datasetId, datacategoryId, and date-range filters; limit 1–1000 (default 25) with offset
  • Returns the location IDs noaa_climate_find_stations and noaa_climate_fetch_data take — FIPS:37, CITY:US530018, ZIP:98101
  • nameContains adds a case-insensitive name match within one category of at most 4,000 locations (every category but ZIP); it fails as name_filter_requires_category without a category and name_filter_category_too_large past the cap

noaa_climate_find_stations tool
  • Filter by locationId, extent (lat/lon bounding box), datasetId, datatypeId (array), and date range; limit 1–1000 (default 25) with offset
  • extent is minLat,minLon,maxLat,maxLon: four finite signed decimal or scientific numbers, with surrounding whitespace allowed, latitude within ±90 and longitude within ±180. Equal coordinates work; reversed axes return no matches and are forwarded unchanged, without antimeridian wrapping.
  • Returns station IDs (GHCND:USW00024233, COOP:010008), names, coordinates, elevation, and data-coverage dates — the IDs feed noaa_climate_fetch_data as stationId

noaa_climate_get_station tool
  • Single required input: stationId, from noaa_climate_find_stations; the tool form of the noaa://stations/{stationId} resource
  • Returns name, coordinates, elevation, and the full data-coverage date range; fails as not_found when a well-formed ID resolves to nothing

noaa_climate_fetch_data tool
  • Requires datasetId, startDate, endDate; optional stationId, locationId, datatypeId arrays. The span cap is 1 year for GHCND, PRECIP_15, PRECIP_HLY, NORMAL_DLY, NORMAL_HLY, NEXRAD2, NEXRAD3 and 10 years for GSOM, GSOY, NORMAL_MLY, NORMAL_ANN; any NORMAL_* dataset takes startDate=2010-01-01 / endDate=2010-12-31
  • Returns flat observation records plus an effectiveQuery echo; date_range_exceeded names the latest maxEndDate CDO will accept. The encoded query ceiling is 4000 characters; longer queries fail as validation_error before any request. Reduce stationId, locationId, and datatypeId filters and make separate calls. Filters are never discarded or automatically split.
  • Request units: "metric" or "standard". Omission preserves NOAA's raw values and adds dataset-specific guidance, including on empty pages. Examples: GHCND TMAX/TMIN use tenths °C, PRCP tenths mm, and SNOW/SNWD whole mm; GSOM/GSOY temperature and precipitation use °C/mm; NORMAL_* temperature normals use tenths °F and precipitation normals hundredths inches; PRECIP_HLY HPCP and PRECIP_15 QPCP use hundredths inches. Units and scale depend on datatype; these examples do not describe wind, direction, counts, percentages, or every snow datatype. See NOAA's dataset documentation.
  • PRECIP_HLY HPCP and PRECIP_15 QPCP missing sentinels become missing: true with value omitted: 99999 without units, 999.99 standard, or 25399.75 metric. Rows, raw attributes, order, totals, and offsets remain intact. Zero, trace, and accumulation-end measurements remain values; flags alone do not mark a row missing. A notice counts missing observations on this page.
  • GHCND attributes remain raw and are also decoded as flags: { measurement, quality, source, observationTime }. Explicit blank slots and leading-zero times are preserved; absent trailing positions remain omitted. A nonblank quality means the observation failed a quality check. A notice counts those rows on this page; numeric values remain available for callers to decide how to aggregate them. Other datasets retain their raw attributes without GHCND decoding. See GHCND's flag layout.

noaa_climate_search_storm_events tool
  • No token required; year selects one export (1950 through the current partial year); filter by episodeId (exact digit string from a returned event; whitespace is trimmed, blank means unset, leading zeros remain significant), state (the full NCEI name, e.g. "FLORIDA"), eventType, month, startDate/endDate, and minDamageInUsd; page ceiling 100 (default 50) with offset
  • Optional startDate/endDate are real YYYY-MM-DD dates and match inclusive event-span overlap before damage accounting, totals, and pagination. One-sided, equal, and cross-year intervals work; only year selects the export. Active date bounds exclude missing, invalid, or reversed source spans; without bounds those rows remain visible. appliedDateRange echoes supplied bounds on both surfaces. Reversed request dates fail as invalid_date_range before downloading.
  • Each distinct episode narrative appears once in `episodeNarrati

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx