Servidor MCP para notificaciones de ntfy.sh, mensajería asíncrona de agentes y flujos de trabajo con intervención humana.
Proporciona una forma sencilla para que un cliente MCP publique mensajes en un tema de ntfy, mantenga una suscripción activa y espere respuestas sin necesidad de crear una capa de mensajería personalizada.
Este servidor es útil cuando necesitas:
notificaciones push desde un agente conectado a MCP
intercambio de mensajes asíncrono entre un usuario y un agente
un ciclo ligero de aprobación o respuesta humana a través de ntfy
un canal de notificación simple para flujos de trabajo de larga duración
Flujo típico:
Un usuario o sistema externo publica un mensaje en un tema de ntfy.
El cliente MCP lo lee a través de wait-and-read-inbox o ntfy://inbox.
El agente responde a través de send-ntfy.
El usuario recibe la respuesta como una notificación push de ntfy.
Related MCP server: Chat Human MCP Server
publicar mensajes con título, prioridad, etiquetas y archivos adjuntos opcionales
mantener una suscripción persistente para una entrega casi en tiempo real
cambiar de tema sin reiniciar el servidor
mantener mensajes recientes en memoria y en disco
soporte para temas protegidos con token de portador (bearer-token) y autenticación básica
funciona con ntfy.sh público de forma inmediata
Instalar globalmente:
npm install -g nfty-mcp-serverO ejecutar a través de npx:
npx -y --yes nfty-mcp-serverCrea o reutiliza un tema en ntfy.sh. Los temas públicos son fáciles de configurar, así que elige un nombre único.
Para Cursor o VS Code, añade esto a tus ajustes de MCP:
{
"mcpServers": {
"nfty": {
"command": "npx",
"args": ["-y", "--yes", "nfty-mcp-server"],
"env": {
"NTFY_TOPIC": "your-topic-name",
"NTFY_BASE_URL": "https://ntfy.sh"
}
}
}
}Para Claude Desktop, añade la misma entrada de servidor a claude_desktop_config.json.
Notas:
NTFY_TOPIC es obligatorio
--yes mantiene las instalaciones de npx en su propia caché en lugar de contaminar el directorio del proyecto
Reinicia Cursor, VS Code o Claude Desktop para que se cargue el servidor MCP.
send-ntfyPublica un mensaje en el tema configurado.
Parámetros:
message obligatorio
title opcional
priority opcional, de 1 a 5
tags opcional
attachUrl opcional
Ejemplo:
{
"message": "Task completed successfully.",
"title": "Task Status",
"priority": 4
}set-ntfy-topicCambia el tema activo para la sesión actual.
Parámetros:
topic obligatorio
baseUrl opcional
wait-and-read-inboxEspera nuevos mensajes en el tema configurado y devuelve el control cuando llega al menos uno.
Parámetros:
since opcional
sinceTime opcional
sinceNow opcional, por defecto true
Importante:
muchos clientes MCP imponen un tiempo de espera de aproximadamente 60 segundos
si estás esperando una respuesta humana, el cliente o el agente que realiza la llamada debe reintentar tras el tiempo de espera
Comportamiento recomendado para los flujos de chat del agente:
Si
wait-and-read-inboxagota el tiempo de espera mientras espera una respuesta del usuario, reintenta hasta que llegue un nuevo mensaje.
ntfy://inboxDevuelve los mensajes recientes del tema configurado en formato JSON.
Forma del ejemplo:
{
"topic": "your-topic",
"baseUrl": "https://ntfy.sh",
"messages": [
{
"id": "message-id",
"time": 1234567890,
"title": "Message Title",
"message": "Message body",
"priority": 3,
"tags": ["tag1"],
"topic": "your-topic"
}
]
}El servidor almacena registros, archivos de caché y archivos de bloqueo en un directorio de datos dedicado para no saturar el proyecto actual.
Ubicación por defecto:
macOS / Linux: ~/.nfty-mcp-server/
Windows: C:\Users\<usuario>\.nfty-mcp-server\
Los archivos escritos allí incluyen:
nfty-messages.json
nfty-debug.log
nfty-process.log
nfty.lock
Variable | Descripción | Por defecto |
| Tema para enviar/recibir mensajes | obligatorio |
| URL del servidor ntfy |
|
| Token de portador (Bearer) | opcional |
| Nombre de usuario para autenticación básica | opcional |
| Contraseña para autenticación básica | opcional |
| Cursor de backlog inicial |
|
| Tiempo de espera de obtención en milisegundos |
|
| Limpiar registros/caché al iniciar |
|
| Matar instancias de servidor existentes |
|
| Sustitución del directorio de datos | ruta de plataforma por defecto |
| Sustitución del archivo de caché |
|
También puedes configurar el servidor directamente:
npx nfty-mcp-server --topic my-topic --base-url https://ntfy.sh --auth-token your-tokenArgumentos soportados:
--topic
--base-url o --server
--auth-token
--username
--password
--since
--log-incoming
El servidor abre una suscripción HTTP persistente al tema configurado.
Los mensajes entrantes se reciben a través de esa conexión en vivo.
Los mensajes recientes se almacenan en caché en la memoria y se guardan en el disco.
Las herramientas MCP exponen el comportamiento de envío, cambio de tema y espera/lectura sobre esa suscripción.
mensajería asíncrona usuario-agente
notificaciones push para tareas de larga duración
ciclos de aprobación humana
alertas ligeras para operadores
coordinación entre agentes a través de un tema compartido
git clone https://github.com/harshwasan/NFTY-MCP.git
cd NFTY-MCP
npm install
npm test
npm run devEstructura del proyecto:
NFTY-MCP/
src/server.js
tests/server.test.js
package.jsonLos mensajes no llegan:
verifica NTFY_TOPIC
confirma que el tema existe y es accesible
inspecciona el registro de depuración en el directorio de datos configurado
Problemas de conexión:
verifica el acceso a la red a la NTFY_BASE_URL configurada
verifica los ajustes de autenticación si el tema está protegido
MIT
Publish a message to the configured ntfy topic (set in mcp.json). Supports optional title, priority (1-5), tags, and attachUrl. After sending, use wait-and-read-inbox to wait for responses.
| Name | Required | Description | Default |
|---|---|---|---|
| tags | No | ||
| title | No | ||
| message | Yes | ||
| priority | No | ||
| attachUrl | No |
| Name | Required | Description |
|---|---|---|
| id | No | |
| time | No | |
| topic | Yes | |
| status | Yes | |
| priority | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It only describes the action as 'publish' without mentioning side effects, idempotency, permission requirements, or rate limits. The description lacks transparency on common behavioral aspects for a send operation.
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 consists of two concise sentences with essential information front-loaded. The first sentence establishes the core purpose, and the second provides a useful cross-reference. No superfluous content.
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 output schema exists, return values need not be explained. The description covers the basic operation but omits potential constraints (e.g., message length, priority semantics) and error scenarios. It assumes the topic is configured in mcp.json without discussing what happens if it's not. Completeness is adequate but not thorough.
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 schema has 0% description coverage, so the description partially compensates by listing all optional parameters and noting priority range (1-5). However, it does not explain the purpose of tags or attachUrl, nor does it provide formats or examples, leaving some semantics unclear.
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 'Publish a message to the configured ntfy topic', specifying the verb and resource. It lists supported optional fields (title, priority, tags, attachUrl). This differentiates it from siblings set-ntfy-topic (configuration) and wait-and-read-inbox (response handling).
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 explicitly advises to use wait-and-read-inbox after sending, providing sequential guidance. It does not discuss when not to use this tool or prerequisites, but the context is clear: it is for sending a message to a preconfigured topic.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Change the ntfy topic for this MCP server session (no restart needed).
| Name | Required | Description | Default |
|---|---|---|---|
| topic | Yes | ||
| baseUrl | No |
| Name | Required | Description |
|---|---|---|
| topic | Yes | |
| baseUrl | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description should disclose behavioral traits. It only mentions 'no restart needed', but does not explain implications of changing topic mid-session, whether the change is persistent, or what happens to ongoing notifications. Lacks detail on side effects and conditions.
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 concise and front-loaded with the core action. However, it could be structured to include more detail without being wasteful; currently it is slightly under-specified for a 2-parameter tool.
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?
The description is adequate for a simple tool but fails to address the baseUrl parameter. Completeness is acceptable for a minimal tool but has a clear gap given the presence of an optional parameter.
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%, so the description must compensate. It explains the 'topic' parameter implicitly but does not mention the 'baseUrl' parameter at all, leaving its purpose unclear for the agent.
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 verb ('Change') and resource ('ntfy topic'), specifying it is for the session and does not require restart. This distinguishes it from siblings send-ntfy and wait-and-read-inbox, which are about message sending and receiving.
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 context (changing topic in session) but does not explicitly state when to use compared to siblings or when not to use it. 'No restart needed' hints at immediate effect but lacks comprehensive guidance on appropriate scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Waits for new messages on the configured topic (set in mcp.json) and returns when a new message arrives. Does not return until at least one new message is received. Uses the existing subscription. Note: The MCP protocol has a ~60s client-side timeout that cannot be controlled from the server, but this tool will wait as long as possible within that limit.
| Name | Required | Description | Default |
|---|---|---|---|
| since | No | Cursor to filter messages after this point | |
| sinceNow | No | If true (default), only returns messages sent after this call starts. If false, returns all messages since the cursor. | |
| sinceTime | No | Unix timestamp - filter messages with time >= sinceTime |
| Name | Required | Description |
|---|---|---|
| messages | Yes | |
| newCount | Yes | |
| lastCursor | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavioral traits: it waits indefinitely (subject to timeout), uses existing subscription, and returns only on new message. No contradictions.
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?
Three concise sentences, front-loaded with the core function, each providing essential information without 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 tool's waiting behavior and 3 parameters, the description covers the key aspects including timeout and return condition. Output schema exists, so return values are covered.
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%, so baseline is 3. The description does not add extra meaning beyond what the input schema already describes for each parameter.
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 (wait for new messages) and resource (inbox on configured topic), and distinguishes from siblings (send-ntfy, set-ntfy-topic) which are different tools.
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 explains that the tool blocks until a new message arrives and notes the client-side timeout, providing clear usage context. However, it does not explicitly state when not to use it or compare with siblings.
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.
v1.0.35send-ntfyset-ntfy-topicwait-and-read-inboxScored across 3 tools
Each tool serves a distinct purpose: sending messages, changing topic, and waiting for incoming messages. No overlap, clear boundaries.
Tool names mix patterns: 'send-ntfy' and 'set-ntfy-topic' use verb-ntfy, but 'wait-and-read-inbox' uses a different structure with 'and'. Inconsistent naming conventions.
Three tools is appropriate for a focused notification server: send, configure topic, and receive. Each tool is necessary and none are redundant.
Core publish/subscribe functionality is covered with send and wait. The set-topic tool adds flexibility. A minor gap is lack of explicit unsubscribe or message history, but not essential for core use.
Push notifications for AI agents - send instant iPhone notifications from any MCP client.
Reach your own phone from an AI agent: notifications, approval questions, reminders, ring, files.
Let your AI agent notify you by email, Slack, Discord, or webhook. One tool: send_notification.
Zero-setup WhatsApp notifications + human-in-the-loop for AI agents — text 'join', send in 60s.
