Apple Notifier MCP Server enables native macOS notifications and system dialog interactions through any MCP-compatible client such as Claude Desktop or Cline. It allows your AI assistant to display notifications, show interactive prompts, use text-to-speech, take screenshots, and open file pickers directly from within your macOS environment.
To install Apple Notifier for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install apple-notifier-mcp --client claude
npm install -g apple-notifier-mcp
For Cline (cline_mcp_settings.json
):
{
"mcpServers": {
"apple-notifier": {
"command": "apple-notifier-mcp"
}
}
}
For Claude Desktop (claude_desktop_config.json
):
{
"mcpServers": {
"apple-notifier": {
"command": "apple-notifier-mcp"
}
}
}
Display native macOS notifications with customizable content.
await client.use_mcp_tool("apple-notifier", "send_notification", {
title: "Hello",
message: "World",
subtitle: "Optional subtitle",
sound: true
});
Parameters:
title
(required): string - The title of the notificationmessage
(required): string - The main message contentsubtitle
(optional): string - A subtitle to displaysound
(optional): boolean - Whether to play the default notification sound (default: true)Show interactive dialog prompts to get user input.
const result = await client.use_mcp_tool("apple-notifier", "prompt_user", {
message: "What's your name?",
defaultAnswer: "John Doe",
buttons: ["OK", "Cancel"]
});
Parameters:
message
(required): string - Text to display in the prompt dialogdefaultAnswer
(optional): string - Default text to pre-fillbuttons
(optional): string[] - Custom button labels (max 3)icon
(optional): 'note' | 'stop' | 'caution' - Icon to displayUse macOS text-to-speech capabilities.
await client.use_mcp_tool("apple-notifier", "speak", {
text: "Hello, world!",
voice: "Samantha",
rate: -20
});
Parameters:
text
(required): string - Text to speakvoice
(optional): string - Voice to use (defaults to system voice)rate
(optional): number - Speech rate (-50 to 50, defaults to 0)Capture screenshots using macOS screencapture.
await client.use_mcp_tool("apple-notifier", "take_screenshot", {
path: "screenshot.png",
type: "window",
format: "png"
});
Parameters:
path
(required): string - Path where to save the screenshottype
(required): 'fullscreen' | 'window' | 'selection' - Type of screenshotformat
(optional): 'png' | 'jpg' | 'pdf' | 'tiff' - Image formathideCursor
(optional): boolean - Whether to hide the cursorshadow
(optional): boolean - Whether to include window shadow (only for window type)timestamp
(optional): boolean - Add timestamp to filenameOpen native macOS file picker dialog.
const files = await client.use_mcp_tool("apple-notifier", "select_file", {
prompt: "Select images",
fileTypes: {
"public.image": ["png", "jpg", "jpeg"]
},
multiple: true
});
Parameters:
prompt
(optional): string - Prompt messagedefaultLocation
(optional): string - Default directory pathfileTypes
(optional): object - File type filter (e.g., {"public.image": ["png", "jpg"]})multiple
(optional): boolean - Allow multiple file selectionThere are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.