What is macos-ecosystem-mcp CLAUDE.md?

Repository instructions for an AI coding assistant working on a macOS Swift MCP server. They explain the server's architecture, tools, commands, dependencies, and release details.

Use them when developing, reviewing, building, or releasing the macos-ecosystem-mcp project.

They provide project-specific rules and background that a general coding assistant would not know.

How neverprepared/macos-ecosystem-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to neverprepared/macos-ecosystem-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/neverprepared/macos-ecosystem-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/neverprepared/macos-ecosystem-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/neverprepared/macos-ecosystem-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/neverprepared/macos-ecosystem-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/neverprepared/macos-ecosystem-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/neverprepared/macos-ecosystem-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/neverprepared/macos-ecosystem-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/neverprepared/macos-ecosystem-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,433 This file is loaded in full into every session.

When invoked 1,433 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.

Model	Per session	Once invoked
Fable 5.1	$0.01433	$0.01433
Opus 5.5	$0.00573	$0.00573
Sonnet 5.5	$0.00287	$0.00287
Haiku 4.5	$0.00143	$0.00143

Measured 2mo ago against content hash f2a523332468, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

macos-ecosystem-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 2mo 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 · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code when working in this repository.

Overview

macos-ecosystem-mcp is a native Swift Model Context Protocol (MCP) server that exposes macOS productivity apps — Reminders, Calendar, Contacts, Notes and iMessage — to MCP clients over stdio. It compiles to a single self-contained binary (macos-mcp); there is no Node.js runtime at run time.

Package name: macos-mcp (executable target of the same name)
Server identity: macos-ecosystem-mcp, version 0.7.0 (hard-coded in App.swift)
Platform: macOS 13+, Swift tools 5.9
Sole dependency: modelcontextprotocol/swift-sdk (from: 0.9.0)
Linked: CoreLocation, Contacts frameworks + sqlite3

Architecture

All source lives in one flat target: Sources/macos-mcp/.

File	Role
`App.swift`	`@main` entry point. Boots managers, requests permissions, registers `ListTools`/`CallTool` handlers, and contains the single `switch` tool dispatcher. Also defines `log()`.
`ToolDefinitions.swift`	`let allTools: [Tool]` — every tool's name, description and JSON input schema.
`EventKitManager.swift`	Reminders + Calendar via EventKit (no subprocess).
`ContactsManager.swift`	Contacts via the Contacts framework.
`NotesHandler.swift`	Notes via `osascript` (Notes.framework is private). Static methods, no instance.
`MessagesManager.swift`	iMessage: reads query `~/Library/Messages/chat.db` (SQLite, read-only); sends go through `osascript`.

Design notes worth knowing before editing:

stdout is reserved for the MCP protocol. All diagnostics go to stderr via log(). Never print() to stdout.
Every tool handler has the shape func name(args: [String: Value]) async throws -> String and returns a plain-text string; dispatch in App.swift wraps it in CallTool.Result and converts thrown errors into isError: true results.
Permissions (EventKit, Contacts) are requested once at startup, before any request is served.
iMessage sending is fail-closed: it is disabled until an allowlist is configured via the MACOS_MCP_IMESSAGE_ALLOWLIST env var (comma-separated) and/or ~/.config/macos-mcp/imessage-allowlist.json ({"allow": [...]}). Phone numbers match on the last 10 digits. Attachments from ~/.config/macos-mcp and ~/Library/Messages are refused. Reading chat.db and sending both require Full Disk Access.

Read the full file on GitHub · 103 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.

2mo ago First seen · 103 lines · 1,433 tokens per session scan A f2a523332468

Subscribe to this mod's changes

macos-ecosystem-mcp CLAUDE.md is an instructions file published in the GitHub repository neverprepared/macos-ecosystem-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,433 tokens to every session, about $0.0057 per session on Opus 5.5. 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 2026-09-09.

Building agents Mobile

macos-ecosystem-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
macos-ecosystem-mcp CLAUDE.mdneverprepared/macos-ecosystem-mcp	Instructions file	1	1mo ago	MIT	A	1,433	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

macos-ecosystem-mcp: Instructions file for Claude Code