MCP Notifications Server
Enables display of native notifications through macOS Notification Center, with support for custom titles, content, icons, and system sounds.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Notifications Servershow a notification titled 'Meeting Reminder' with message 'Team sync in 10 minutes' and use the Ping sound"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Notifications Server
A Model Context Protocol (MCP) server that enables Claude and other MCP clients to display native macOS notifications.
Features
show_notification tool for displaying notifications on macOS
Support for custom titles and content
Optional icon and sound parameters
Uses macOS Notification Center
Related MCP server: Notifications MCP Server
Prerequisites
Node.js (v18 or later)
macOS (for notification support)
npm or yarn
Installation
Clone or download this repository
Install dependencies:
npm installBuild the TypeScript code:
npm run buildUsage with Claude Desktop
Add this server to your Claude Desktop configuration file:
Location: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"notifications": {
"command": "node",
"args": ["/Users/konstantinzagulin/IdeaProjects/mcp-notifications/build/index.js"]
}
}
}Replace the path with the actual path to your installation.
Tool: show_notification
Display a notification on macOS.
Parameters
title (required): The title of the notification
content (required): The main message content
icon (optional): Path to an icon file (e.g.,
/path/to/icon.png)sound (optional): System sound name to play (e.g.,
Ping,Basso,Hero,Funk,Glass,Pop,Submarine,Blow,Bottle,Frog,Morse,Purr,Sosumi,Tink)
Example Usage
In Claude Desktop, you can ask Claude to show notifications:
Show me a notification with title "Task Complete" and message "Your build finished successfully"Display a notification titled "Reminder" with the message "Meeting in 5 minutes" and use the Ping soundDevelopment
Project Structure
mcp-notifications/
├── src/
│ └── index.ts # Main MCP server implementation
├── build/ # Compiled JavaScript (generated)
├── package.json
├── tsconfig.json
└── README.mdBuilding
npm run buildTesting Locally
You can test the server by running it directly:
node build/index.jsThe server communicates via stdio, so you'll need an MCP client to interact with it properly.
How It Works
This MCP server uses:
@modelcontextprotocol/sdk: Official MCP SDK for TypeScript
node-notifier: Cross-platform notification library that uses macOS Notification Center on macOS
The server exposes a single tool (show_notification) that accepts notification parameters and displays them using the native macOS notification system.
License
MIT
Available Tools
1 toolshow_notificationC
Display a notification on macOS using the Notification Center. Can include a title, content message, and optional icon and sound.
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | The title of the notification | |
| content | Yes | The main content/message of the notification | |
| icon | No | Optional path to an icon file to display with the notification | |
| sound | No | Optional name of a system sound to play (e.g., 'Ping', 'Basso', 'Hero', 'Funk') |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. While it mentions the tool displays a notification with optional features, it lacks critical details such as system requirements (macOS only), user permissions needed, whether it's synchronous/asynchronous, error handling, or visual/auditory behavior specifics. This leaves significant gaps in understanding how the tool behaves in practice.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded, stating the core purpose in the first sentence and listing key features efficiently. However, it could be slightly more structured by separating mandatory and optional parameters explicitly, though this is minor.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (4 parameters, no output schema, no annotations), the description is minimally adequate. It covers what the tool does but lacks depth on behavioral aspects, error cases, or integration context. Without annotations or output schema, more detail on expected outcomes or limitations would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, meaning all parameters are documented in the schema. The description adds minimal value by listing parameters (title, content, icon, sound) but doesn't provide additional semantics like examples beyond the schema's sound enum suggestions or practical usage tips. Baseline 3 is appropriate as the schema handles most documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Display a notification on macOS using the Notification Center.' It specifies the verb ('Display') and resource ('notification'), and mentions key capabilities (title, content, optional icon and sound). However, with no sibling tools provided, there's no opportunity to distinguish from alternatives, preventing a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, prerequisites, or typical use cases. It merely lists what the tool does without context for application, leaving the agent to infer usage scenarios independently.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
1 tool update
v1.0.0- First observed
show_notification
TDQS
With only one tool, there is no possibility of ambiguity or overlap between tools, as there are no other tools to compare it to. The tool's purpose is clearly defined and distinct by default.
Since there is only one tool, naming consistency is inherently perfect. The tool name 'show_notification' follows a clear verb_noun pattern, and there are no other tools to create inconsistency.
A single tool is generally too few for a server's purpose, as it limits functionality and may indicate an incomplete or trivial implementation. For a notifications server, one tool feels thin and under-scoped, lacking operations like managing or dismissing notifications.
The tool surface is severely incomplete for a notifications domain. While 'show_notification' covers creation, there are obvious gaps such as listing, updating, or dismissing notifications, which are essential for a full notifications lifecycle. This will likely cause agent failures in more complex workflows.
Maintenance
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
Push notifications for AI agents - send instant iPhone notifications from any MCP client.
Search, read, and write your Apple Notes from ChatGPT/Claude via a local Mac agent + MCP relay.
- mcp-serverOAuthnet.vybit
Push notifications with personalized sounds - manage and trigger your vybits via MCP
MCP connector for iMessage & Contacts via a local Mac agent + Vercel relay
Related MCP Servers
- AlicenseNot gradedqualityCmaintenancemacOS Notification MCP enables AI assistants to trigger native macOS sounds, visual notifications, and text-to-speech. Built for Claude and other AI models using the Model Context Protocol.37MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to send native macOS notifications for task completion alerts and reminders. Supports interactive features like custom system sounds, action buttons, and user replies directly from the notification center.201MIT
- AlicenseBqualityDmaintenanceEnables AI assistants to send desktop notifications on macOS with rich formatting, urgency levels, and sound options.1261MIT
- AlicenseAqualityDmaintenanceMCP server that lets Claude Desktop or another MCP client trigger macOS sound and visual notifications through a task_status tool.116MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/konstzv/mcp-notifications'
If you have feedback or need assistance with the MCP directory API, please join our Discord server