Skip to main content
Glama
msageryd

mcp-macos-utils

by msageryd
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

mcp-macos-utils

A Model Context Protocol (MCP) server that provides macOS utility tools for AI assistants.

Features

  • Native macOS Notifications: Send system notifications with different types (success, error, info, warning)

  • Auto Project Detection: Automatically detects and includes the current project name in notifications

  • Notification Logging: All notifications are logged to ~/.mcp-notifications.log for audit trail

  • TypeScript Support: Fully typed for better development experience

Related MCP server: nucleus-apple-mcp

Installation

  1. Clone this repository:

git clone <repository-url>
cd mcp-macos-utils

  1. Run the install script:

./install.sh

This will:

  • Install npm dependencies

  • Build the TypeScript code

  • Create an example configuration file

Configuration

Add the following to your MCP client's configuration file:

{
  "mcpServers": {
    "macos-utils": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-macos-utils/dist/index.js"],
      "env": {}
    }
  }
}

Replace /absolute/path/to/mcp-macos-utils with the actual path to this directory.

Usage

Once configured, the following tool will be available to AI assistants:

notify

Send a macOS notification with project context.

Parameters:

  • title (required): The notification title

  • message (required): The notification message

  • type (optional): Type of notification - success, error, info, or warning (default: info)

  • sound (optional): Whether to play a sound (default: true)

  • subtitle (optional): Custom subtitle (defaults to current project name)

Example:

await notify({
  title: "Build Complete",
  message: "Your project has been built successfully",
  type: "success"
});

Notification Types

  • Success (✅): For successful operations

  • Error (❌): For errors or failures

  • Warning (⚠️): For warnings or cautions

  • Info (ℹ️): For general information

Logging

All notifications are logged to ~/.mcp-notifications.log in JSON format, including:

  • Timestamp

  • Project name

  • Notification type

  • Title and message

  • Any errors that occurred

Development

Building

npm run build

Development Mode

npm run dev

Clean Build

npm run clean
npm run build

Requirements

  • macOS (uses native osascript for notifications)

  • Node.js 20+

  • TypeScript 5.5+

License

MIT

Available Tools

1 tool
notifyA

Send a macOS notification with auto-detected project context

ParametersJSON Schema
NameRequiredDescriptionDefault
titleYesNotification title
messageYesNotification message
typeNoType of notification (affects icon)info
soundNoWhether to play a sound
subtitleNoOptional subtitle (defaults to project name)

TDQS

A3.7/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'auto-detected project context,' which adds useful context about behavior beyond basic notification sending. However, it lacks details on permissions required, system dependencies, or how the auto-detection works, leaving gaps for a tool that interacts with the macOS system.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the core functionality ('Send a macOS notification') and adds the distinctive feature ('with auto-detected project context'). There is zero waste, making it highly concise and well-structured for quick understanding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (5 parameters, macOS system interaction) and no annotations or output schema, the description is minimally complete. It covers the basic purpose and a key behavioral trait but lacks details on error handling, return values, or system requirements, which could hinder effective use by an AI agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the input schema fully documents all parameters. The description does not add any meaning beyond the schema, such as explaining how 'auto-detected project context' relates to parameters like 'subtitle.' Baseline score of 3 is appropriate as the schema handles the heavy lifting without extra value from the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Send a macOS notification') and the key feature ('with auto-detected project context'), making the purpose immediately understandable. It distinguishes this as a macOS-specific notification tool with contextual awareness, which is precise and actionable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for macOS notifications with project context, but provides no explicit guidance on when to use this tool versus alternatives (e.g., other notification methods or platforms). Since there are no sibling tools, the lack of comparative guidance is less critical, but it still offers only implied context without exclusions or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.6/5.0
Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'notify' has a clearly defined and distinct purpose.

Naming Consistency5/5

A single tool inherently has perfect naming consistency, as there are no other tools to compare it against. The name 'notify' is clear and follows a simple verb pattern.

Tool Count2/5

A single tool is too few for a server named 'mcp-macos-utils', which implies a broader set of macOS utility functions. This feels thin and incomplete for the apparent scope.

Completeness2/5

Given the server name suggests macOS utilities, the single notification tool leaves significant gaps. There are no tools for other common macOS operations like file management, system info, or automation, making the surface severely incomplete.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • macOS Notify MCP

    yuki-yano
    A
    license
    B
    quality
    F
    maintenance
    An MCP server that enables AI assistants like Claude to send native macOS notifications with tmux integration, allowing notifications to focus specific tmux sessions when clicked.
    3
    17
    14
    MIT

  • mcp-ding

    zhuqingyv
    F
    license
    Not graded
    quality
    D
    maintenance
    MCP server for macOS native notifications with 67 AI brand icons and system sound support, enabling AI agents to send desktop notifications via one-line tool calls.

  • mcp-os-notifications

    ekomac
    A
    license
    B
    quality
    C
    maintenance
    An MCP server that lets LLM agents dispatch native OS notifications when a task finishes. It supports cross-platform desktop notifications, task tokens for updates, mobile bridges, and quiet hours.
    2
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/msageryd/mcp-macos-utils'

If you have feedback or need assistance with the MCP directory API, please join our Discord server