macOS Utilities
Provides macOS utility tools for AI assistants, including sending native notifications with project context.
mcp-macos-utils
A Model Context Protocol (MCP) server that provides macOS utility tools for AI assistants.
Features
- Native macOS Notifications: Send system notifications with different types (success, error, info, warning)
- Auto Project Detection: Automatically detects and includes the current project name in notifications
- Notification Logging: All notifications are logged to
~/.mcp-notifications.logfor audit trail - TypeScript Support: Fully typed for better development experience
Installation
- Clone this repository:
git clone <repository-url>
cd mcp-macos-utils
- Run the install script:
./install.sh
This will:
- Install npm dependencies
- Build the TypeScript code
- Create an example configuration file
Configuration
Add the following to your MCP client's configuration file:
{
"mcpServers": {
"macos-utils": {
"command": "node",
"args": ["/absolute/path/to/mcp-macos-utils/dist/index.js"],
"env": {}
}
}
}
Replace /absolute/path/to/mcp-macos-utils with the actual path to this directory.
Usage
Once configured, the following tool will be available to AI assistants:
notify
Send a macOS notification with project context.
Parameters:
title(required): The notification titlemessage(required): The notification messagetype(optional): Type of notification -success,error,info, orwarning(default:info)sound(optional): Whether to play a sound (default:true)subtitle(optional): Custom subtitle (defaults to current project name)
Example:
await notify({
title: "Build Complete",
message: "Your project has been built successfully",
type: "success"
});
Notification Types
- Success (✅): For successful operations
- Error (❌): For errors or failures
- Warning (⚠️): For warnings or cautions
- Info (ℹ️): For general information
Logging
All notifications are logged to ~/.mcp-notifications.log in JSON format, including:
- Timestamp
- Project name
- Notification type
- Title and message
- Any errors that occurred
Development
Building
npm run build
Development Mode
npm run dev
Clean Build
npm run clean
npm run build
Requirements
- macOS (uses native
osascriptfor notifications) - Node.js 20+
- TypeScript 5.5+
License
MIT
Server Terkait
Kone.vc
sponsorMonetize your AI agent with contextual product recommendations
Backlog MCP Server
An MCP server for interacting with the Backlog API, a project management and collaboration tool.
Planfix
An MCP server for integrating with the Planfix project management and CRM platform.
Confluence
Provides secure access to Atlassian Confluence content and spaces using its REST API.
CalmBoard.ai
MCP - Multi-purpose endpoint for AI agents to access CalmBoard's features and data. This MCP provides a comprehensive interface for AI agents to interact with CalmBoard's project/scrum/kanban board management functionalities and retrieve relevant data to provide insights and recommendations to users.
Routine
MCP server to interact with Routine: calendars, tasks, notes, etc.
LAPRAS MCP Server
An MCP server for lapras.com, providing access to career-related tools.
Monday.com
Interact with Monday.com boards, items, updates, and documents.
mcp-me
Your AI assistants don't know who you are. mcp-me fixes that: a local MCP server that gives any AI a full picture of who you are
Yandex Tracker
Interact with Yandex Tracker APIs for issue management and search.
WxO Agent MCP
Simple MCP (Model Context Protocol) server that invokes a single Watson Orchestrate agent remotely. The agent is defined once via environment variables or MCP config. Use this when you want a lightweight MCP that only chats with one agent—no tool management, no agent listing, no flows. Just invoke_agent(message) and get_agent().