AppleScript MCP
Execute AppleScript to gain full control of your Mac.
AppleScript MCP Server (Dual access: python and node.js)
Overview
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
Features
- Run AppleScript to access Mac applications and data
- Interact with Notes, Calendar, Contacts, Messages, and more
- Search for files using Spotlight or Finder
- Read/write file contents and execute shell commands
- Remote execution support via SSH
Example Prompts
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
Usage with Claude Desktop
Node.js
{
"mcpServers": {
"applescript_execute": {
"command": "npx",
"args": [
"@peakmojo/applescript-mcp"
]
}
}
}
Python (uvx)
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"
]
}
}
}
Python (local development)
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"
]
}
}
}
Development
Setup
brew install uv
uv sync --dev
Run all checks (in parallel)
uv run check
This runs linting, formatting, type checking, and tests with 100% coverage — all in parallel.
Individual commands
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
Docker Usage
When running in a Docker container, you can use the special hostname host.docker.internal to connect to your Mac host:
Configuration
{
"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:
- SSH is enabled on your Mac (System Settings → Sharing → Remote Login)
- Your user has proper permissions
- The correct credentials are provided in the config
Servidores relacionados
Kone.vc
patrocinadorMonetize your AI agent with contextual product recommendations
PowerPoint Translator
Translate PowerPoint files using AWS Bedrock. Requires AWS credentials to be configured.
Things
Interact with your task management data in the Things app.
Prompt Buddy
Prompt Buddy MCP exposes a public, searchable catalog of reusable AI skills.
IWE
Knowledge graph MCP server for searching, reading, and refactoring hierarchical markdown documents
Xwiki MCP
MCP server for XWiki REST API — read your wiki from Claude and other AI agents
Portfolio Manager MCP Server
A server providing tools and resources for managing and analyzing investment portfolios.
pubmed-mcp-server
PubMed biomedical literature
APITier MCP Server
MCP server exposing 10 APITier utility APIs as AI agent tools
CodeRide
Task management redesigned for AI, integrated via the CodeRide MCP server.
Mesh Scanner
A simple, self-contained notes system with resources, tools, and prompts, implemented as an MCP server.