Macos Automator MCP
M

Macos Automator MCP

This project provides a server based on the Model Context Protocol (MCP) that supports remote execution of AppleScript and JavaScript automation scripts on macOS. It includes a rich knowledge base of predefined scripts and can control macOS applications and system functions.
2.5 points
5.0K

What is the macOS Automator MCP Server?

This is a service that allows remote execution of macOS automation scripts via the Model Context Protocol (MCP). It supports two scripting languages, AppleScript and JavaScript for Automation (JXA), and provides a preset script library that can control system applications such as Finder and Safari to complete various automation tasks.

How to use this service?

You can configure and connect to this server through an MCP client, and then send JSON - formatted requests to execute scripts. Three execution methods are supported: directly running script code, calling script files, or using scripts from the preset script library.

Applicable scenarios

Suitable for scenarios that require automated control of the macOS system, such as batch file processing, web page automation, automatic email processing, system settings adjustment, and other repetitive work automation.

Main features

Script execution
Supports the execution of AppleScript and JXA scripts, which can be invoked in three ways: by code, file, or preset script ID.
Preset script library
Provides a rich preset script library covering automation operations of common applications such as Finder, Safari, and Mail.
Remote control
Enables remote script execution via the MCP protocol and can be integrated into automation workflows.
Advantages
Achieve macOS automation without developing a complete application
The preset script library provides out - of - the - box common automation functions
Supports two scripting languages (AppleScript/JXA) to meet different needs
Can be easily integrated into existing systems via the MCP protocol
Limitations
Requires configuration of macOS automation permissions, which is more complex for first - time use
Some advanced functions require system permissions to execute
The debugging tools for JXA are not as perfect as those for AppleScript

How to use

Install the service
Install via npm or run the server directly
Configure the MCP client
Add server connection information to the MCP client configuration file
Set permissions
Grant automation and accessibility permissions to the application running the service (such as Terminal) in the system settings
Execute scripts
Send JSON requests via the MCP protocol to execute scripts

Usage examples

Get the URL of the current Safari tab
Get the URL address of the currently open tab in the Safari browser via a preset script
Create a folder on the desktop
Use Finder to create a new folder with the specified name on the desktop
Send an email
Send an email via the Mail application

Frequently Asked Questions

Why does script execution fail?
How to add custom scripts?
What should I do if script execution times out?

Related resources

GitHub repository
Project source code and issue tracking
AppleScript Language Guide
Official AppleScript language reference
JXA Getting Started Guide
Learning resources for JavaScript for Automation

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "macos_automator": {
      "command": "npx",
      "args": [
        "-y",
        "@steipete/macos-automator-mcp@latest"
      ]
    }
  }
}

{
      "mcpServers": {
        "macos_automator_local": {
          "command": "/absolute/path/to/your/cloned/macos-automator-mcp/start.sh",
          "env": {
            "LOG_LEVEL": "DEBUG"
          }
        }
      }
    }
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

R
Rsdoctor
Rsdoctor is a build analysis tool specifically designed for the Rspack ecosystem, fully compatible with webpack. It provides visual build analysis, multi - dimensional performance diagnosis, and intelligent optimization suggestions to help developers improve build efficiency and engineering quality.
TypeScript
9.1K
5 points
N
Next Devtools MCP
The Next.js development tools MCP server provides Next.js development tools and utilities for AI programming assistants such as Claude and Cursor, including runtime diagnostics, development automation, and document access functions.
TypeScript
9.9K
5 points
T
Testkube
Testkube is a test orchestration and execution framework for cloud-native applications, providing a unified platform to define, run, and analyze tests. It supports existing testing tools and Kubernetes infrastructure.
Go
5.5K
5 points
M
MCP Windbg
An MCP server that integrates AI models with WinDbg/CDB for analyzing Windows crash dump files and remote debugging, supporting natural language interaction to execute debugging commands.
Python
9.1K
5 points
R
Runno
Runno is a collection of JavaScript toolkits for securely running code in multiple programming languages in environments such as browsers and Node.js. It achieves sandboxed execution through WebAssembly and WASI, supports languages such as Python, Ruby, JavaScript, SQLite, C/C++, and provides integration methods such as web components and MCP servers.
TypeScript
9.4K
5 points
N
Netdata
Netdata is an open-source real-time infrastructure monitoring platform that provides second-level metric collection, visualization, machine learning-driven anomaly detection, and automated alerts. It can achieve full-stack monitoring without complex configuration.
Go
9.9K
5 points
M
MCP Server
The Mapbox MCP Server is a model context protocol server implemented in Node.js, providing AI applications with access to Mapbox geospatial APIs, including functions such as geocoding, point - of - interest search, route planning, isochrone analysis, and static map generation.
TypeScript
9.0K
4 points
U
Uniprof
Uniprof is a tool that simplifies CPU performance analysis. It supports multiple programming languages and runtimes, does not require code modification or additional dependencies, and can perform one-click performance profiling and hotspot analysis through Docker containers or the host mode.
TypeScript
7.3K
4.5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
22.6K
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
65.4K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
32.2K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
18.8K
4.5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
59.2K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
29.0K
5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
20.6K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
42.7K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase