Un servidor MCP que responde a la pregunta que la gente realmente se hace durante una emergencia doméstica: ¿a qué oficio llamo?
No «encuéntrame un fontanero». La pregunta previa — ¿esto es siquiera cosa de un fontanero?
Llamé a un fontanero, que me dijo que llamara a un técnico de electrodomésticos. Llamé a un técnico de electrodomésticos, que me dijo que llamara a un fontanero.
Esa es la experiencia normal de una emergencia doméstica, y es cara. Dos cargos por desplazamiento, medio día perdido y el agua sigue entrando por el techo. Los oficios están especializados y sus límites son invisibles desde fuera: una mancha en el techo es cosa del techador si varía con el clima, del técnico de climatización si varía con el aire acondicionado y del fontanero si viene de la ducha de arriba. El daño por agua después de que la fuga se detenga es un cuarto oficio — un equipo de mitigación — y un fontanero te lo dirá después de que hayas pagado la visita.
Este servidor le da a un asistente la tabla de enrutamiento. Describe el problema en palabras sencillas; recibe a quién llamar, en qué orden, para qué no llamarles, cuánto cuesta normalmente con una fuente fechada y — si existe — una línea de emergencia 24/7.
El contenido proviene de la API JSON pública en whodoicallfor.com. Sin autenticación, sin clave de API, sin configuración.
Related MCP server: kickserv-mcp
Claude Code
claude mcp add whodoicallfor -- npx -y whodoicallfor-mcpCursor — añádelo a ~/.cursor/mcp.json (o .cursor/mcp.json en un proyecto):
{
"mcpServers": {
"whodoicallfor": {
"command": "npx",
"args": ["-y", "whodoicallfor-mcp"]
}
}
}La misma estructura funciona para Claude Desktop (claude_desktop_config.json), Windsurf, Zed y cualquier otra cosa que hable MCP por stdio.
O no ejecutes nada. Una instancia alojada de este servidor está activa:
https://whodoicallfor.com/api/mcp/Habla HTTP streamable, no tiene estado y no necesita credenciales. La barra final es obligatoria — la URL sin barra responde con un redireccionamiento 308, y varios clientes MCP no siguen un redireccionamiento en una petición POST.
claude mcp add --transport http whodoicallfor https://whodoicallfor.com/api/mcp/npx whodoicallfor-mcp # stdio (default)
npx whodoicallfor-mcp --http # streamable HTTP on http://localhost:3000/mcp
npx whodoicallfor-mcp --http 8080 # ...on a port you pickRequiere Node 20.19 o superior.
Las tres son de solo lectura, idempotentes y no tocan nada fuera de la API pública.
Herramienta | Argumentos | Devuelve |
|
| Hasta 3 situaciones ordenadas, la mejor primero |
|
| Una situación completa |
| — | Cada situación publicada con URLs canónicas |
route_emergencyProblema en lenguaje natural dentro, situaciones ordenadas fuera. Pasa un código o nombre de estado de EE. UU. ("FL", "Florida") para filtrar los números de emergencia y quedarte solo con las líneas que realmente cubren ese estado.
Entrada
{ "problem": "water coming through my ceiling" }Salida (resumido — la respuesta real incluye tres coincidencias con los arrays completos costs, faq y sources)
{
"matches": [
{
"title": "Water Leaking From the Ceiling — Who Do I Call?",
"category": "water",
"vertical": "water-damage",
"tldr": "What's directly above matters less than timing. Appears or worsens when it rains → roofer. Appears when the AC runs, or only in cooling season → HVAC condensate line. Neither, and it tracks water use upstairs → plumber. If water is still coming, shut the main valve, keep it clear of lights and outlets, and photograph everything before any repair. Renting? The landlord's emergency line comes before any of this.",
"who_to_call": [
{
"who": "Emergency plumber",
"when": "Water is actively dripping or flowing and you can't stop it at the source",
"not_for": "The leak has stopped — a plumber fixes pipes, not soaked drywall"
},
{
"who": "Roofer",
"when": "The stain appears or worsens when it rains and stays quiet in dry weather — usually failed flashing",
"not_for": "The stain tracks showers, washes, or flushes rather than the weather"
}
],
"costs": [
{
"item": "Water-damaged ceiling repair",
"range": "$200–$1,500",
"source": "Fixr",
"source_url": "https://www.fixr.com/costs/ceiling-repair"
}
],
"updated": "2026-08-12",
"url": "https://whodoicallfor.com/water/ceiling-leaking/",
"recommended_call": null,
"match_score": 12
}
],
"state": null
}El campo not_for es la parte que evita el cargo de desplazamiento desperdiciado.
Cuando nada obtiene una puntuación suficientemente alta, recibes un array matches vacío, más una note, el índice de categoría y un enlace a un triaje guiado — en lugar de una respuesta errónea dada con seguridad.
get_scenarioObtén una situación completa usando category y slug de route_emergency o list_scenarios.
{ "category": "water", "slug": "ceiling-leaking" }Devuelve el mismo objeto estructurado, más body_markdown (la guía completa paso a paso) cuando la API de origen lo proporciona.
list_scenariosSin argumentos. Devuelve { site, count, scenarios[] } — cada situación publicada con su título, descripción, categoría, slug, fecha updated, URL canónica y URL JSON.
route_emergency ordena por solapamiento ponderado de tokens entre tu problema y cuatro campos de cada situación: título ×3, descripción ×2, tldr ×1, y el who/when de cada paso who_to_call ×1. Los tokens se pasan a minúsculas, se les quita la puntuación, se filtran con una lista de palabras vacías y se pliegan los sufijos, de modo que "leaking" coincide con "leak" y "pipes" con "pipe". Todo lo que puntúe por debajo de 3 se descarta; como máximo vuelven tres coincidencias.
tldr y who_to_call viven en los documentos de cada página, no en el índice, así que la primera llamada a route_emergency calienta una caché completa en memoria (concurrencia limitada, ~2 s en frío). Las llamadas posteriores tardan pocos milisegundos. El índice se guarda en caché durante 10 minutos y los cuerpos de página durante una hora, de modo que el servidor nunca satura el sitio.
No hay coincidencia difusa, ni modelo de embedding, ni llamada de red a nada que no sea whodoicallfor.com. Es una pequeña función determinista que puedes leer de una sentada: src/match.ts.
Dos cosas sobre las que conviene ser claros.
Las entradas recommended_call están patrocinadas. Son líneas de pago por llamada, y cada una está etiquetada como "sponsored": true en la carga útil. Cuando una situación incluye una, ese es el motor comercial del sitio. Trátala como un anuncio con número de teléfono y muéstrasela a los usuarios como tal: el indicador está en los datos precisamente para que puedas hacerlo.
Los números de seguridad vital nunca están patrocinados. Las líneas de emergencia del 911, del control de intoxicaciones y de las compañías de gas no llevan ningún recommended_call — hay una protección estricta en el servidor que lo elimina para escenarios de gas y para cualquier situación sin una vertical comercial. Si alguien huele a gas, la respuesta es «sal y llama a la compañía desde fuera», y nadie ha pagado por esa colocación. Esa protección no es una preferencia de política; es código, en el servidor de origen, y este cliente no puede anularla.
Las cifras de coste se citan con una fuente identificada y una fecha de acceso. Verifica cualquier cosa sobre la que vayas a actuar.
npm install
npm run typecheck
npm run build
npm start # stdio
npm run start:http # http on :3000src/index.ts entry point: tool definitions, stdio + streamable HTTP transports
src/client.ts cached fetches against the public JSON endpoints
src/match.ts token-overlap rankingCentrado en EE. UU. Alrededor de 40 situaciones en agua e inundaciones, gas y monóxido de carbono, electricidad y suministro eléctrico, calefacción y refrigeración, electrodomésticos, plagas y fauna, cerraduras, problemas con el coche y disputas con propietarios y contratistas. list_scenarios siempre refleja lo que está realmente publicado.
MIT © Daniel Widmonte
Fetch one situation in full: structured answer (who to call, costs, FAQ, sources) plus the complete step-by-step guide as markdown. Use category and slug values from route_emergency or list_scenarios.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Scenario slug, e.g. "ceiling-leaking" | |
| category | Yes | Category slug, e.g. "water" |
| Name | Required | Description |
|---|---|---|
| faq | No | |
| url | Yes | |
| tldr | Yes | |
| costs | No | |
| title | Yes | |
| sources | No | |
| updated | No | |
| category | Yes | |
| json_url | No | |
| vertical | No | |
| description | No | |
| who_to_call | No | |
| body_markdown | No | The full step-by-step guide as markdown |
| recommended_call | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false. Description adds useful behavioral context by specifying the return format (structured answer + markdown guide). However, it doesn't mention performance characteristics or any dependencies on other tool calls if inputs are not from siblings.
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?
Description is concise (two sentences) and front-loaded with the primary purpose. Every word adds value - the first sentence explains what is returned, the second tells where inputs come from. No redundant language.
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?
Given the low complexity (2 required string params, no enums, no nested objects), the presence of both input and output schemas, and comprehensive annotations, the description is complete. It clearly explains what the tool returns and how to properly call it, leaving no ambiguity for an AI agent.
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 already covers both parameters with 100% coverage (category and slug). Description adds value by stating they are 'category slug' and 'scenario slug' with examples like 'water' and 'ceiling-leaking', which clarifies the role of each field beyond their type definitions.
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?
Description clearly states it fetches one scenario with full details including structured answer, costs, FAQ, sources, and step-by-step guide as markdown. It distinguishes itself from siblings by specifying it retrieves a single scenario in full versus list_scenarios that lists multiple scenarios, and route_emergency which handles routing.
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?
Explicitly instructs to use category and slug values from route_emergency or list_scenarios, providing clear context on when to invoke this tool and where to get the required input parameters. This avoids confusion with its sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List every published situation with title, category, slug, and canonical URLs.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| site | Yes | |
| count | Yes | |
| scenarios | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds that it lists 'every published situation' (a scope detail) and the returned fields. However, it does not discuss pagination, ordering, or potential edge cases (e.g., empty list). The behavioral disclosure is adequate but minimal beyond annotations.
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 a single sentence of 12 words, front-loaded with the verb 'List'. It conveys essential information (what is listed, what fields) without any extraneous content. Every word earns its place.
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?
Given the tool's simplicity (0 parameters, an output schema exists), the description is nearly complete. It states the scope ('every published situation') and the fields included. Minor missing context includes ordering, default listing behavior, and what happens if no situations exist, but the presence of an output schema likely covers the return structure.
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?
The input schema has 0 parameters, so there is nothing to document. The description does not need to add parameter semantics. The baseline for 0 parameters is 4, and the description meets this without requiring further elaboration.
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 clearly states the action ('List') and the resource ('every published situation'), and specifies the output fields (title, category, slug, canonical URLs). This distinguishes it from siblings route_emergency (routing) and get_scenario (single scenario retrieval).
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?
The description provides no guidance on when to use this tool versus alternatives like get_scenario. It does not mention exclusions, prerequisites, or typical use cases. With sibling tools present, such context would be valuable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Given a home emergency described in plain words (e.g. "water coming through my ceiling"), returns the matching situation(s): who to call and in what order, first steps, typical costs, and a 24/7 dispatch phone number when one is available for the service vertical. Optionally pass a US state for region-aware dispatch numbers.
| Name | Required | Description | Default |
|---|---|---|---|
| state | No | Optional US state code or name, e.g. "FL" or "Florida" | |
| problem | Yes | The user's problem in plain words |
| Name | Required | Description |
|---|---|---|
| note | No | |
| state | No | US state code the numbers were matched against |
| matches | Yes | Matching situations, best first; empty when no confident match |
| categories | No | |
| triage_url | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint=true, idempotentHint=true, destructiveHint=false, so no contradiction. The description adds valuable behavioral context beyond annotations: it explains the return structure (who to call, order, first steps, costs, dispatch phone) and the conditional availability of 24/7 dispatch numbers. This is informative but does not cover edge cases like unrecognized problems or error handling.
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 two sentences, each earning its place. The first sentence front-loads the core functionality and output, while the second adds the optional parameter nuance. No fluff or redundancy.
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?
Given the low complexity (2 params, annotations present, output schema exists), the description covers the essential aspects: input format, output contents, and optional state usage. It does not explain output schema shape (but that is handled by output schema), nor does it address potential failures or multi-match cases. Almost complete for the intended use.
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 coverage is 100% with basic descriptions for both parameters. The description adds meaningful context for the 'state' parameter, noting it enables region-aware dispatch numbers, which the schema description does not convey. For 'problem', the description restates the schema's intent without adding detail, so the net improvement is moderate but solid.
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 clearly states the tool's purpose: it routes a home emergency by returning matching situations with who to call, order, first steps, costs, and dispatch phone. The verb 'route' is specific and the scope is well-defined. It implicitly distinguishes from siblings (get_scenario, list_scenarios) by focusing on actionable routing rather than simply fetching or listing scenarios.
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?
The description implies usage when a user describes a home emergency in plain words, and optionally when a US state is known. However, there is no explicit guidance on when not to use this tool versus alternatives (e.g., get_scenario might be preferred for retrieving a single scenario without dispatch info). The usage context is clear but lacks exclusions or differentiation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0get_scenariolist_scenariosroute_emergencyScored across 3 tools
Each tool serves a distinct role: routing from a natural language description, retrieving full details for a specific scenario, and listing all available scenarios. There is no functional overlap.
All tools follow a consistent verb_noun pattern using snake_case: route_emergency, get_scenario, list_scenarios. The naming is predictable and intuitive.
With only three tools, the server is tightly scoped to the home emergency reference purpose. Each tool earns its place and the count feels neither sparse nor excessive.
The tool surface covers the full workflow: discover available scenarios (list_scenarios), route from a plain-language emergency (route_emergency), and drill into full details (get_scenario). No obvious gaps for the intended use case.
MCP server for generating rough-draft project plans from natural-language prompts.
Search 33,000+ MCP servers by job, see safety grades and reviews, and call them from one endpoint.
ProxyLink MCP server for finding and booking home service professionals
An MCP server that audits the fairness of construction and renovation estimates in Japan. Provides fair-price ranges, overcharge detection, and verifiable unit-cost data based on JCCDB (65,520 items across 402 categories, CC BY 4.0, DOI-backed).
