How does this server differ from Google Calendar or iCloud integrations?
It operates entirely locally using macOS Apple Events, with no OAuth tokens, no cloud relays, and no requirement to expose private iCloud data.
@jayaprakashnarayana
Basic information
An MCP (Model Context Protocol) server that securely integrates with the native macOS Calendar application. It allows AI models to read events and create new events securely using AppleScript without complex dependencies.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mac-calendar": {
"command": "uvx",
"args": [
"--from",
"mac-calendar-mcp",
"mac-calendar-mcp"
]
}
}
}A native, zero-dependency bridge between Claude (or any MCP client) and your local macOS Calendar app. Your calendar data never leaves your machine, unlike cloud-based integrations that require OAuth or expose iCloud data.
No complex installation is required. Add the following configuration to your claude_desktop_config.json file under mcpServers: use the uvx command with the provided Git repository and module name.
list_calendars, get_events, and add_event.It operates entirely locally using macOS Apple Events, with no OAuth tokens, no cloud relays, and no requirement to expose private iCloud data.
The first run requires manually granting UI permission via macOS Transparency, Consent, and Control (TCC). Nothing can access your calendar silently.
No, all data is read and written locally on your Mac. Your calendar data never leaves your machine.
None beyond macOS and an MCP client. The server is a zero-dependency solution.
Yes, it is designed as a bridge for any MCP client, though the quick setup example shows Claude Desktop configuration.

Employee scheduling for multi-location teams: shifts, coverage, time off and tasks. Changes wait for approval by default, within existing role and location limits.
WhatsMCP — WhatsApp for AI agents. Put an AI agent on a real WhatsApp number. Expose regular WhatsApp accounts to your LLM agents over JSON-RPC. A complete Model Context Protocol server that turns phone numbers into addr

AI-native operating system for general contractors: estimates, takeoff, bids, pay apps.

Write LinkedIn posts in your own voice from Claude, ChatGPT, or any MCP client. ContentIn trains a personal AI on your own LinkedIn posts, then generates ideas, drafts in your voice, schedules, publishes via LinkedIn's o
Find the AI tells in your prose. Deterministic, local, runs in CI. MCP server + CLI + Action.
Comments