Macos Notify MCP
M

Macos Notify MCP

An MCP server tool for macOS notifications, supporting native notifications and tmux integration, allowing AI assistants to send clickable notifications and focus on specific tmux sessions.
2.5 points
5.8K

What is macOS Notify MCP?

macOS Notify MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude to send native macOS notifications and focus on specific tmux sessions when clicked. This tool implements the notification function through the UserNotifications API and can automatically identify terminal applications (such as VSCode, iTerm2, etc.).

How to use macOS Notify MCP?

After installation, you can send notifications through the command line or integrate it into an AI assistant (such as Claude Code). Users can specify the notification content, title, sound, and the tmux session and window to focus on.

Applicable scenarios

It is suitable for developers who need to interact with the terminal, especially those who use tmux for multitasking. It can be used to remind users of build completion, test passing, or task completion.

Main features

Native macOS notifications
Use the UserNotifications API of macOS to send system-level notifications, ensuring a consistent notification experience.
Clickable notifications
After clicking the notification, it can focus on the specified tmux session, facilitating quick switching of the working environment.
Terminal detection
Automatically detect the currently used terminal application (such as VSCode, iTerm2, etc.) to ensure that the correct program is opened when the notification is triggered.
Customizable sounds
Support selecting different notification sounds to meet the preferences of different users.
Multi-session support
Support sending multiple notifications simultaneously, and each notification can independently focus on different tmux sessions.
Advantages
Provide a native macOS notification experience, enhancing the user experience.
Support multiple terminal applications, with strong compatibility.
Easy to integrate into AI assistants (such as Claude Code).
Support customizable sounds and notification content, with high flexibility.
Limitations
Only support the macOS system and are not applicable to other operating systems.
Need to install tmux to implement the full tmux session focusing function.
For users who are not familiar with the command line, the configuration may be a bit complicated.

How to use

Installation
First, install Node.js and tmux (if you need the tmux function). Then, globally install macOS Notify MCP through npm.
Configure the AI assistant
Add the MCP server to the configuration file of the AI assistant, such as `claude_desktop_config.json` of Claude Desktop.
Send notifications
Use the command-line tool to send notifications. You can specify the message, title, sound, and tmux session information.

Usage examples

Build completion notification
Send a notification to remind developers when the project build is completed.
Test passing notification
Send a notification after the test passes to help developers quickly confirm the result.
Task completion notification
Send a notification after the task is completed to remind developers of the next operation.

Frequently Asked Questions

How to install macOS Notify MCP?
Why is the notification not displayed?
How to specify a tmux session?
Which terminal applications are supported?

Related resources

GitHub repository
Project source code and documentation
README.md
Detailed technical documentation
Installation guide
Detailed installation instructions

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "macos-notify": {
      "command": "macos-notify-mcp"
    }
  }
}
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
8.8K
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
8.4K
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
6.2K
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
8.6K
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
7.5K
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
9.6K
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
7.7K
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
8.3K
4.5 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
18.9K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
62.2K
4.3 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
21.7K
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
32.3K
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#
27.0K
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
57.6K
4.5 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
19.9K
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
41.3K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase