push-notification-mcp
Sends native macOS push notifications via a single MCP tool, using osascript for secure delivery.
README
push-notification-mcp
A local MCP server that sends push notifications on macOS.
Quick Start
pnpm install && pnpm run build && npx @anthropic-ai/mcpb pack .
Drag the .mcpb into Claude Desktop or any MCPB-compatible client of your choice.
Specification
NOTE: This project was generated from an NLSpec (included) and was wholly implemented (or "dark-complied") by a Claude model (code formatting not included) as an experiment/initial evaluation of the NLSpec approach (see below). Also
An NLSpec (as la the @TG-Techie flavor) is a prescriptive, generative specification written in natural language — precise enough to derive a faithful implementation from, flexible enough to leave genuine implementation choices to the builder. For background on the approach, see the strongdm/attractor repo where the concept was developed in practice.
How It Works
The server exposes a single MCP tool — send_notification — over stdio. When called, it delivers a native macOS notification displaying a title and body. The notification mechanism is osascript with display notification, invoked via execFile (no shell). User input is passed as argv to the AppleScript on run argv handler — never interpolated into script text.
Installation
As an MCPB Bundle
Build and pack:
pnpm install && pnpm run build && npx @anthropic-ai/mcpb pack .
This produces a .mcpb file you can install in Claude Desktop or any MCPB-compatible client.
As a Standalone MCP Server
Add to your MCP client configuration:
{
"mcpServers": {
"push-notification": {
"command": "node",
"args": ["/absolute/path/to/push-notification-mcp/dist/index.js"]
}
}
}
Or if published to npm:
{
"mcpServers": {
"push-notification": {
"command": "npx",
"args": ["-y", "push-notification-mcp"]
}
}
}
Run Directly
npm install
npm run build
node dist/index.js
The server communicates over stdio (stdin/stdout). Diagnostic logs go to stderr.
Environment Variables
All configuration is optional. The server works out of the box with sensible defaults.
| Variable | Type | Default | Description |
|---|---|---|---|
PUSH_NOTIFICATION_RATE_LIMIT_ENABLED |
boolean | true |
Set to false or 0 to disable rate limiting |
PUSH_NOTIFICATION_RATE_LIMIT_BURST |
integer | 5 |
Token bucket capacity (max burst) |
PUSH_NOTIFICATION_RATE_LIMIT_REFILL_MS |
integer | 12000 |
Milliseconds between token refills |
Boolean values accept true/1 (truthy) and false/0 (falsy), case-insensitive. Integer values must be positive; invalid values are ignored and defaults are used, with a warning logged to stderr.
With defaults: burst of 5 notifications, then sustained rate of ~5 per minute (one every 12 s). The bucket refills continuously — idle for 60 s and it's full again.
Platform
macOS only. The notification delivery mechanism (osascript display notification) is available on all default macOS installations. macOS may prompt you to allow notifications from "Script Editor" — this is expected.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.