The Applescript MCP server enables AI models to execute AppleScript code on macOS systems, providing access to native Mac applications and system functions including Notes, Calendar, Contacts, Messages, Finder, and Spotlight. It offers tools to interact with Mac applications, manage files, execute shell commands, and perform system operations like taking screenshots or checking battery status, while supporting both local and remote execution via SSH. The server solves the problem of giving AI assistants direct control over macOS automation tasks with minimal setup required, available through both Python and Node.js implementations.
A Model Context Protocol (MCP) server that lets you run AppleScript code to interact with Mac. This MCP is intentionally designed to be simple, straightforward, intuitive, and require minimal setup.
I can't believe how simple and powerful it is. The core code is <100 line of code.
https://github.com/user-attachments/assets/b85e63ba-fb26-4918-8e6d-2377254ee388
Create a reminder for me to call John tomorrow at 10am
Add a new meeting to my calendar for Friday from 2-3pm titled "Team Review"
Create a new note titled "Meeting Minutes" with today's date
Show me all files in my Downloads folder from the past week
What's my current battery percentage?
Show me the most recent unread emails in my inbox
List all the currently running applications on my Mac
Play my "Focus" playlist in Apple Music
Take a screenshot of my entire screen and save it to my Desktop
Find John Smith in my contacts and show me his phone number
Create a folder on my Desktop named "Project Files"
Open Safari and navigate to apple.com
Tell me how much free space I have on my main drive
List all my upcoming calendar events for this week
{
"mcpServers": {
"applescript_execute": {
"command": "npx",
"args": [
"@peakmojo/applescript-mcp"
]
}
}
}
No clone needed — run directly from the git repo:
{
"mcpServers": {
"applescript_execute": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/peakmojo/applescript-mcp",
"mcp-server-applescript"
]
}
}
}
For local development, clone the repo and use uv to run from source:
brew install uv
git clone https://github.com/peakmojo/applescript-mcp.git
{
"mcpServers": {
"applescript_execute": {
"command": "uv",
"args": [
"--directory",
"/path/to/your/repo",
"run",
"mcp-server-applescript"
]
}
}
}
brew install uv
uv sync --dev
uv run check
This runs linting, formatting, type checking, and tests with 100% coverage — all in parallel.
uv run lint # ruff linter
uv run format # ruff auto-format
uv run typecheck # pyrefly type checker
uv run test # pytest with 100% coverage enforcement
When running in a Docker container, you can use the special hostname host.docker.internal to connect to your Mac host:
{
"mcpServers": {
"applescript_execute": {
"command": "npx",
"args": [
"@peakmojo/applescript-mcp",
"--remoteHost", "host.docker.internal",
"--remoteUser", "yourusername",
"--remotePassword", "yourpassword"
]
}
}
}
This allows your Docker container to execute AppleScript on the Mac host system. Make sure:
makafeli/n8n-workflow-builder
danishashko/make-mcp
lukisch/n8n-manager-mcp
io.github.us-all/airflow
io.github.infoinlet-marketplace/mcp-workflow