MCP Servers

macPilot

MacPilot CLI is an open-source tool that enables interaction with macOS through the MCP. It provides a collection of system tools that allow AI assistants to perform various operations on macOS systems, including mouse control, screenshots, text pasting, application launching, and more.

huhu415

OS Automation

Visit Server

README

MacPilot CLI

MacPilot CLI is an open-source tool that enables Large Language Models (LLMs) to interact with macOS through the MCP (Model Control Protocol) protocol. It provides a collection of system tools that allow AI assistants to perform various operations on macOS systems.

Tool Documentation

Tool Name	Description	Input Parameters
`repeat`	Echo back the input text	`text`: String to repeat
`getCursorPosition`	Returns the current mouse position and screen details	None
`moveCursor`	Moves the mouse cursor to specific coordinates	`x`: X coordinate, `y`: Y coordinate
`clickMouse`	Performs a mouse click at the current cursor position	None
`pasteText`	Copies text to clipboard and pastes it	`text`: Text to paste
`captureScreen`	Takes a screenshot of the entire screen	None
`executeCommand`	Runs a shell command and returns the output	`command`: Command to execute, `args`: Optional arguments array
`launchApp`	Launches an application	`bundleId & Application identifier` or `appName & Application name`
`getAppsList`	Returns a list of installed applications	None
`getWindowsList`	Returns information about all windows	None
`getFocusedWindowInfo`	Returns information about the focused window	None
`getWindowInfo`	Returns detailed information about a window	`pid`: Optional process ID

Getting Started

You need a Mac computer with Apple Silicon running macOS 14.0 (Sonoma) or later
Download the binary file from the Releases section

Configure your MCP-compatible application (Cursor or Claude Desktop app) by adding the following configuration:

{
  "mcpServers": {
    "macPilotCli": {
      "command": "/path/to/downloaded/binary"
    }
  }
}

Grant the necessary permissions (screen recording, accessibility) to the application you're using with MacPilot CLI. For example, if you're using Cursor, make sure Cursor has the required permissions in System Settings.
Switch to a tool-compatible model according to your application's requirements, and you're ready to use MacPilot CLI

Recommended Servers

Claude Code MCP

An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface.

Featured

Local

JavaScript

@kazuph/mcp-taskmanager

Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.

Featured

Local

JavaScript

Beamlit MCP Server

An MCP server implementation that enables seamless integration between Beamlit CLI and AI models using the Model Context Protocol standard.

Official

TypeScript

ThingsPanel MCP

An integration server that connects AI models with ThingsPanel IoT platform, allowing AI assistants to interact with IoT devices through natural language for device control, data retrieval, and management operations.

Official

Python

systemd-coredump MCP Server

Enables MCP-capable applications to access, manage, and analyze system core dumps through integration with systemd-coredump functionality.

Local

JavaScript

Terminal Controller for MCP

An MCP server that enables secure terminal command execution, directory navigation, and file system operations through a standardized interface for LLMs.

Local

Python

Apple Shortcuts Server

An MCP Server Integration with Apple Shortcuts

Local

JavaScript

mac-apps-launcher

An MCP server to list and launch applications on MacOS

Local

JavaScript

applescript-mcp

Enables LLM applications to interact with macOS through AppleScript.

Local

TypeScript

Bazel MCP Server

A local MCP server that exposes Bazel build system functionality to AI agents, allowing them to build, test, query, and manage Bazel projects through natural language even in environments where Bazel can't be directly accessed.

Local

JavaScript