apple-calendar-mcp: Instructions file for Claude Code

CLAUDE.md

apple-calendar-mcp CLAUDE.md is an instructions file for Claude Code from redpop/apple-calendar-mcp. It costs 2,141 tokens per session, scanned A, original, MIT.

Project instructions for an Apple Calendar integration on macOS. The project combines a Swift command-line helper using EventKit with a TypeScript layer that exposes calendar access through the MCP protocol.

In plain words
What is it for?
It is for building, testing, type-checking, signing, and updating the Apple Calendar MCP server and its Swift helper.
Why use it?
It gives developers the commands, build requirements, architecture constraints, and important signing details needed to test and package the integration correctly on both Apple-silicon and Intel Macs.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is redpop/apple-calendar-mcp's own configuration. It tells Claude Code how to work on apple-calendar-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything apple-calendar-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to redpop/apple-calendar-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/redpop/apple-calendar-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/redpop/apple-calendar-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for apple-calendar-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/redpop/apple-calendar-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/redpop/apple-calendar-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/redpop/apple-calendar-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/redpop/apple-calendar-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for apple-calendar-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/redpop/apple-calendar-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/redpop/apple-calendar-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,141 This file is loaded in full into every session.
When invoked 2,141 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.02141 $0.02141
Opus 5 $0.01071 $0.01071
Sonnet 5 $0.00428 $0.00428
Haiku 4.5 $0.00214 $0.00214

Measured 8d ago against content hash 927b9e1e4206, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

apple-calendar-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

An MCP server exposing Apple Calendar on macOS to any client that speaks the protocol. Two halves: a Swift CLI wrapping EventKit, and a TypeScript MCP layer that drives it.

Commands

npm test                                  # full vitest suite
npx vitest run tests/freeTime.test.ts     # one file
npx vitest run -t "ignoriert abgesagte"   # one test by name
npm run typecheck                         # tsc --noEmit (covers src/ and tests/)
npm run build                             # tsc -> dist/ (src/ only)
./swift/build.sh                          # compile + sign bin/calendar-helper (universal)

build.sh builds both arm64 and x86_64 against a macOS 14 deployment target and joins them with lipo. The binary ships inside the npm package, so an arm64-only build would be broken on Intel Macs — and only at the user's end, never at build time. Signing happens on the finished fat binary; lipo would invalidate per-slice signatures anyway.

After changing swift/main.swift, run ./swift/build.sh and restart the client. There is no service to reinstall — the helper is a child process of the MCP server, so the next server start picks up the new binary.

After changing src/, run npm run build and restart the client; it loads dist/index.js once at startup.

vitest.config.ts pins TZ=Europe/Berlin. Several tests assert literal +02:00 timestamps. Do not make those assertions timezone-agnostic — the offset is part of what they verify.

The architecture constraint that explains everything

macOS attributes calendar (TCC) permission to the responsible parent process, not to the binary being executed. A GUI client like Claude Desktop declares no calendar usage description anywhere in its bundle, so any process it spawns is denied — silently, with no dialog and no entry in System Settings.

The helper escapes this by disclaiming that responsibility at startup. reexecDisclaimed() in swift/main.swift re-execs the process via posix_spawn(POSIX_SPAWN_SETEXEC) with responsibility_spawnattrs_setdisclaim, making the binary its own TCC-responsible process. macOS then reads the usage description from its embedded Info.plist and prompts under the name calendar-helper. This is the same private libSystem call Chromium uses for its helper processes; it is resolved through dlsym, so a future macOS dropping the symbol degrades to the old behaviour instead of failing to load.

Read the full file on GitHub · 88 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 88 lines · 2,141 tokens per session scan A 927b9e1e4206

Subscribe to this mod's changes

apple-calendar-mcp CLAUDE.md is an instructions file published in the GitHub repository redpop/apple-calendar-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,141 tokens to every session, about $0.0107 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens