Skip to main content
Glama
deenesjakoruzh
Cactusinhand

MCP Notify Server

by Cactusinhand
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Versión de PyPI

📢 Servidor de notificaciones MCP

inglés |中文

Un servidor MCP que envía notificaciones de escritorio con efectos de sonido cuando se completan las tareas del agente.

🥩 Características

  • Enviar notificaciones de escritorio del sistema después de que se completen las tareas del agente

  • Reproduce sonidos de alerta para captar la atención del usuario, con un archivo de sonido dentro.

  • Compatibilidad multiplataforma (Windows, macOS, Linux)

  • Basado en el protocolo MCP estándar, se integra con varios clientes LLM

Related MCP server: Notifications MCP Server

⏬ Instalación

Instalar usando el administrador de paquetes uv

git clone https://github.com/Cactusinhand/mcp_server_notify.git
cd mcp_server_notify

uv venv
source .venv/Scripts/activate

uv pip install mcp-server-notify
# or
pip install mcp-server-notify

Después de la instalación, llame al módulo directamente para verificar si la instalación fue exitosa:

python -m mcp_server_notify

Este módulo acepta la opción --debug o --file , podemos usarlo así:

python -m mcp_server_notify --debug
python -m mcp_server_notify --debug --log-file=path/to/logfile.log

⚠️❕ Requisitos especiales

** Usamos la API de Apprise para la entrega de notificaciones de escritorio, por lo que necesitamos instalar algunos requisitos especiales en nuestro escritorio **

Ventanas

# windows:// minimum requirements
pip install pywin32

macOS

# Make sure terminal-notifier is installed into your system
brew install terminal-notifier

📚 Uso

Uso con Claude Desktop:

Encuentra el archivo de configuración claude_desktop_config.json

{
    "mcpServers": {
        "NotificationServer": {
            "command": "uv",
            "args": [
              "--directory",
              "path/to/your/mcp_server_notify project",
              "run",
              "mcp-server-notify",
            ]
        }
    }
}

Si se instala globalmente, también puedes usar el comando de Python:

{
    "mcpServers": {
        "NotificationServer": {
            "command": "python",
            "args": [
              "-m",
              "mcp_server_notify",
            ]
        }
    }
}

⚡️ Uso con cursor:

Busque el archivo de configuración ~/.cursor/mcp.json o your_project/.cursor/mcp.json

{
    "mcpServers": {
        "NotificationServer": {
            "command": "uv",
            "args": [
              "--directory",
              "path/to/your/mcp_server_notify project",
              "run",
              "mcp-server-notify",
            ]
        }
    }
}

Después de la configuración, simplemente agregue un mensaje como finally, send me a notification when task finished. Al final de su tarea, ingrese a la IA para activar las notificaciones.

En Cursor, puedes agregar esta indicación como una regla en Cursor Settings -> Rules para no tener que escribirla manualmente cada vez.

⚡️ Uso con VSCode + Copilot:

  1. Instalar el administrador de servicios uv/uvx : pip install uv

  2. Agregue el servicio a la configuración de VSCode:

    Windows %APPDATA%\Code\User\settings.json
    macOS $HOME/Library/Application\ Support/Code/User/settings.json
    Linux $HOME/.config/Code/User/settings.json

    "mcp": {
    "servers": {
        "notifier": {
            "command": "uvx",
            "args": [
                "mcp-server-notify"
            ],
            "env": {}
        }
    }
}

  3. Asegúrate de estar usando la última versión de VSCode: ejecuta automáticamente los servicios MCP

  4. Abra VSCode → habilite Copilot → cambie al modo agente.

  5. Escribe # → verás la opción #send_notification.

  6. Pregúntele al agente: ejecute #send_notification (manejará la notificación automáticamente).

  7. Ahora el Copilot en modo agente puede enviar notificaciones de escritorio.

🐳 Ejecutando con Docker

Actualmente no disponible debido a problemas de compatibilidad con el entorno. Si los contenedores Docker necesitan activar notificaciones del host independientemente de si el sistema operativo del host es Windows, macOS o Linux, la solución se vuelve mucho más compleja y el uso directo de notificaciones nativas no suele ser viable.

Cuestiones principales:

  1. Sistemas de notificación específicos del sistema operativo Cada sistema operativo (Windows, macOS, Linux) tiene su mecanismo de notificación único.

  2. Aislamiento de Docker El aislamiento de los contenedores Docker limita su capacidad para acceder directamente a los recursos del sistema operativo host.

  3. Gestión de dependencias Es necesario gestionar diferentes bibliotecas de notificaciones y dependencias para cada sistema operativo.

🧾 Licencia

Instituto Tecnológico de Massachusetts (MIT)

💻 Contribuciones

¡Los problemas y las solicitudes de extracción son bienvenidos!

Available Tools

1 tool
send_notificationC

Send system notification with optional sound

ParametersJSON Schema
NameRequiredDescriptionDefault
titleYes
messageYes
play_soundNo
timeoutNo

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It states the tool sends a notification but doesn't disclose behavioral traits like whether it's synchronous/asynchronous, what happens on failure, if it requires specific permissions, or how notifications are delivered. 'Optional sound' hints at a feature but lacks details on default behavior or sound types.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with a single sentence that directly states the tool's function. It's front-loaded and wastes no words, making it easy to parse quickly. Every part of the sentence contributes to understanding the tool's purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations, no output schema, and 0% schema description coverage for 4 parameters, the description is incomplete. It covers the basic action but lacks details on behavior, parameters, return values, or error handling. For a notification-sending tool with multiple parameters, more context is needed to guide effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the description doesn't add meaning beyond what the schema provides. It mentions 'optional sound' which corresponds to the 'play_sound' parameter, but doesn't explain other parameters like 'title', 'message', or 'timeout'. With 4 parameters and no schema descriptions, the description fails to compensate adequately, resulting in a baseline score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('send') and resource ('system notification') with an additional feature ('optional sound'). It's specific about what the tool does, though without sibling tools, differentiation isn't applicable. The purpose is unambiguous but could be more detailed about the notification type or system context.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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, such as appropriate contexts, prerequisites, or alternatives. It mentions 'optional sound' but doesn't explain when sound should be enabled or disabled. With no sibling tools, this is less critical, but still lacks usage context.

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. 1 tool update
    • First observedsend_notification
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.1/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'send_notification' has a clear, distinct purpose that cannot be confused with any other tool in the set.

Naming Consistency5/5

The tool name 'send_notification' follows a clear verb_noun pattern (send + notification). Since there is only one tool, consistency is inherently perfect with no deviations or mixed conventions to evaluate.

Tool Count2/5

A single tool is too few for a server named 'MCP Notify Server', which suggests a broader notification domain. This minimal set feels thin and likely incomplete for typical notification workflows, such as managing notifications or checking statuses.

Completeness2/5

The tool surface is severely incomplete for a notification server. While 'send_notification' covers sending, there are obvious gaps like listing notifications, updating them, deleting them, or configuring notification settings, which agents would need for full functionality.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches