mcpapp1
mcpapp1 — Servidor MCP meteorológico
Un pequeño servidor Model Context Protocol que expone alertas meteorológicas de EE. UU. en vivo a clientes MCP como Claude Desktop, Claude Code y Cursor.
Los datos provienen de la National Weather Service API, que es gratuita y no requiere clave de API.
Qué expone
Tipo | Nombre | Descripción |
Herramienta |
| Alertas meteorológicas activas para un estado de EE. UU., por código de dos letras (p. ej. |
Recurso |
| Repite un mensaje; útil para verificar que el servidor es accesible |
Related MCP server: Weather MCP Server
Requisitos
Python 3.13+
Configuración
git clone https://github.com/eyosiasbisrat/mcpapp1.git
cd mcpapp1
uv syncEjecución
Ejecuta el servidor directamente a través de stdio:
uv run server/weather.pyO mediante la CLI de MCP:
uv run mcp run server/weather.pyInspecciónalo de forma interactiva en el MCP Inspector:
uv run mcp dev server/weather.pyUn servidor MCP se comunica mediante JSON-RPC a través de stdin/stdout, por lo que ejecutarlo a mano simplemente espera en silencio la entrada. Eso es lo esperado — normalmente un cliente lo inicia por ti.
Conectar un cliente
Claude Code / Cursor
Ambas configuraciones ya están incluidas en el repositorio y usan rutas relativas, por lo que funcionan después de uv sync sin necesidad de ediciones:
.mcp.json — Claude Code
.cursor/mcp.json — Cursor
Recarga la ventana del editor y aprueba el servidor cuando se te solicite.
Claude Desktop
uv run mcp install server/weather.pyA continuación, cierra Claude Desktop por completo — incluido el icono de la bandeja, ya que cerrar la ventana lo deja en ejecución — y vuelve a abrirlo.
Si esto imprime Claude app not found mientras Claude Desktop está claramente instalado, consulta más abajo.
Solución de problemas
Claude app not found en Windows
mcp install busca la configuración de Claude Desktop en una ubicación fija:
%APPDATA%\ClaudeSi Claude Desktop se instaló como un paquete MSIX / Microsoft Store, sus datos se redirigen al contenedor del paquete y ese directorio nunca existe:
%LOCALAPPDATA%\Packages\Claude_<id>\LocalCache\Roaming\Claude\claude_desktop_config.jsonHay dos formas de resolverlo.
Edita la configuración real directamente — añade una entrada mcpServers al claude_desktop_config.json en la ruta del paquete indicada arriba, manteniendo intactas las claves existentes.
O une las rutas una vez con un junction de directorio, tras lo cual mcp install funciona con normalidad para todos los servidores:
cmd /c mklink /J "%APPDATA%\Claude" "%LOCALAPPDATA%\Packages\Claude_<id>\LocalCache\Roaming\Claude"Sustituye Claude_<id> por el nombre real de la carpeta del paquete. Para deshacerlo, cmd /c rmdir "%APPDATA%\Claude" elimina solo el enlace, no la configuración.
Al registrar el servidor manualmente en Windows, usa la ruta absoluta de uv (p. ej. C:\Users\<you>\.local\bin\uv.exe). Las aplicaciones empaquetadas no heredan de forma fiable el PATH de tu shell, por lo que un uv a secas puede no iniciarse.
Verificar que el servidor está realmente cargado
Confirma que el cliente lo ha lanzado comprobando el proceso padre:
Get-CimInstance Win32_Process -Filter "Name='uv.exe'" | ForEach-Object {
$p = Get-CimInstance Win32_Process -Filter "ProcessId=$($_.ParentProcessId)"
"$($_.ProcessId) <- $($p.Name)"
}Un uv.exe cuyo padre es Claude.exe significa que el servidor se está ejecutando. Ten en cuenta que algunas versiones de Claude Desktop no escriben registros por servidor en logs\, por lo que una carpeta de registros vacía no es evidencia de fallo.
Estructura del proyecto
server/weather.py the MCP server: tool, resource, and NWS client
main.py placeholder entrypoint
.mcp.json Claude Code server config
.cursor/mcp.json Cursor server config
pyproject.toml dependencies (httpx, mcp[cli])Notas
get_alertssolo cubre estados de EE. UU., ya que NWS es una agencia estadounidense.Las solicitudes incluyen una cabecera
User-Agent, que la NWS API requiere.Los errores de red y HTTP se capturan y aparecen como un mensaje amigable "unable to fetch" en lugar de un traceback.
Available Tools
1 toolget_alertsA
Get weather alerts for a US state.
Args: state: Two-letter US state code (e.g. CA, NY)
| Name | Required | Description | Default |
|---|---|---|---|
| state | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. 'Get' implies a read-only operation, but the description does not explicitly state side-effect-free behavior or any caveats about alert types or data source. It is not misleading, but it adds minimal behavioral context beyond what the name implies.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise, with a front-loaded purpose statement followed by a compact Args block. Every sentence earns its place and there is no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With a single well-documented parameter, an output schema, and no siblings, the description plus schema fully covers what an agent needs to invoke the tool correctly. No missing context for this simple operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, yet the description fully compensates by specifying the parameter format ('Two-letter US state code') and providing concrete examples ('CA, NY'). This adds real meaning beyond the raw schema type string.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb ('Get'), a clear resource ('weather alerts'), and a clear scope ('US state'). It is unambiguous and leaves no doubt about what the tool does, even without siblings to differentiate from.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There are no sibling tools, so explicit routing guidance is unnecessary. The description clearly implies usage: when you need weather alerts for a US state. It lacks explicit exclusions, but nothing is misleading or missing for a tool of this simplicity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v0.1.0- First observed
get_alerts
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or misselection. The tool's purpose is clearly defined in its name and description.
The single tool name follows the verb_noun pattern (get_alerts), which is clean and predictable. There are no other tools to create inconsistency.
One tool feels thin for a server, even one dedicated to weather alerts. While alerts retrieval is a focused task, a small set of supporting tools (e.g., list states or get alert details) would make the server feel more complete.
For the stated purpose of retrieving weather alerts, the get_alerts tool covers the core operation without obvious gaps. The domain is narrow, and no additional lifecycle operations are necessary for read-only alert access.
Related MCP Connectors
Hosted MCP server for Xweather weather data: conditions, forecasts, alerts, and more.
Get US weather forecasts, active alerts, and current observations.
NOAA and ECMWF weather forecast MCP for discovery, validation, and GribStream OAuth queries.
Smarter Weather MCP: forecasts, alerts, outlooks, observations, AQI, grids, and map imagery.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceThis is a Model Context Protocol (MCP) server that provides weather information using the National Weather Service (NWS) API. Features Get weather alerts for a US state Get weather forecast for a specific location (using latitude and longitude)-
- FlicenseNot gradedqualityDmaintenanceEnables users to get real-time weather alerts for US states and echo messages through both MCP server tools and a modern web interface. Provides weather information access with multiple deployment options for different use cases.1-
- AlicenseBqualityDmaintenanceProvides weather forecasts and alerts for US locations using the National Weather Service API. Enables users to retrieve active alerts by state and detailed forecasts by coordinates via MCP tools.122ISC
- FlicenseNot gradedqualityCmaintenanceEnables querying live U.S. National Weather Service alerts by state through MCP, with both Python and TypeScript implementations.-