Macos Screen MCP
An MCP service for screen view and control on macOS, providing window screenshot, window search, and keyboard input functions, supporting operations by window title or ID.
rating : 2.5 points
downloads : 7.6K
What is the macOS Screen MCP Server?
This is a service specifically designed for the macOS system that enables your applications or AI assistants to view and control windows on the screen. It can automatically identify windows and take screenshots, and also simulate keyboard input operations.How to use the macOS Screen MCP Server?
Simply install the service and configure it in your AI tools (such as Claude or Cursor), and you can obtain window screenshots or control windows through simple commands.Use Cases
Suitable for scenarios that require automated screen operations, such as automated testing, remote assistance, AI-assisted operations, etc. Particularly suitable for developers, testers, and users of efficiency tools.Main Features
Window Screenshot
Capture screenshots of specific windows by window title or ID, supporting binary or Base64 format output.
Window Management
List all visible windows or find specific windows by title.
Keyboard Input Simulation
Supports sending single keys or key combinations, as well as inputting text strings.
Advantages
Simple and easy-to-use API interface
Supports multiple keyboard operations and shortcuts
Can precisely control specific windows
Lightweight service with low resource consumption
Limitations
Only supports the macOS system
Requires user authorization for screen recording permissions
Some special windows may not be captured
How to Use
Install the Service
Install the macos_screen_mcp package via pip
Run the Service
Start the MCP server
Configure AI Tools
Add the MCP server configuration in the settings of Claude or Cursor
Usage Examples
Capture a Browser Window
When you need to obtain the content of the current browser window
Automated Text Input
When you need to input text in the current active window
Frequently Asked Questions
Why doesn't the screenshot function work?
Which keyboard shortcuts are supported?
Related Resources
GitHub Repository
Project source code and latest updates
MCP Protocol Documentation
Official documentation of the Model Context Protocol

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
14.8K
4.5 points

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
24.8K
5 points

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
15.6K
4.3 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
43.6K
4.3 points

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#
20.3K
5 points

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
44.6K
4.5 points

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
15.0K
4.5 points

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
29.4K
4.8 points

