applescript-mcp CLAUDE.md

Project instructions for an MCP server that lets AI assistants run AppleScript on macOS, with Node.js and Python implementations.

In plain words
What is it for?
Working on a server that controls Mac applications, searches files, reads or writes files, runs shell commands, or executes scripts on another Mac over SSH.
Why use it?
They explain how the two implementations and execution modes fit together, reducing the risk of changing one version without updating the other.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/peakmojo/applescript-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/peakmojo/applescript-mcp
Per session 1,164 This file is loaded in full into every session.
When invoked 1,164 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01164 $0.01164
Opus 5 $0.00582 $0.00582
Sonnet 5 $0.00233 $0.00233
Haiku 4.5 $0.00116 $0.00116

Measured 2d ago against content hash c86a36f9fe26, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

applescript-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 2d 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 · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project Overview

This is the AppleScript MCP (Model Context Protocol) Server - a dual-implementation MCP server that allows AI assistants to execute AppleScript on macOS systems. The server is available in both Node.js and Python implementations.

Key Capabilities:

  • Execute AppleScript to interact with macOS applications (Notes, Calendar, Contacts, Messages, Mail, etc.)
  • Search files using Spotlight/Finder
  • Read/write file contents and execute shell commands
  • Remote execution via SSH
  • Docker support with host.docker.internal for Mac host access

Architecture

Dual Implementation

The project provides two parallel implementations:

  1. Node.js (server.js): Primary implementation using @modelcontextprotocol/sdk
  2. Python (src/applescript_mcp/server.py): Alternative implementation using Python MCP SDK

Both implementations provide identical functionality and should be kept in sync.

Core Components

server.js (Node.js)

  • Main entry point: Implements MCP tool applescript_execute
  • Execution modes:
    • Local: Uses /usr/bin/osascript to run AppleScript files
    • Remote: Uses SSH (node-ssh) to execute on remote Mac hosts
  • Configuration via CLI args: --remoteHost, --remoteUser, --remotePassword
  • Logging via custom Logger class (levels: ERROR, WARN, INFO, DEBUG)

Key Functions:

  • executeAppleScript(code, timeout): Determines local vs remote execution
  • executeLocalAppleScript(code, timeout): Executes on local machine
  • executeRemoteAppleScript(code, timeout): Executes via SSH connection

Development Guidelines

Code Style

  • Keep implementations simple and minimal (currently <100 LOC for core logic)
  • Use proper error handling - return error messages rather than throwing
  • Always clean up temporary files
  • Log important operations at appropriate levels

When Making Changes

  1. Maintain Dual Implementation Parity: If you modify the Node.js version, apply equivalent changes to the Python version and vice versa.

Read the full file on GitHub · 149 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. 2d ago First seen · 149 lines · 1,164 tokens per session scan A c86a36f9fe26

Subscribe to this mod's changes

applescript-mcp CLAUDE.md is an instructions file published in the GitHub repository peakmojo/applescript-mcp (462 stars, last pushed 6mo ago), licensed MIT. It adds 1,164 tokens to every session, about $0.0058 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 2026-08-30.

Related

Other instructions, from other repositories

apple-notes-mcp CLAUDE.md

Instructions for sweetrb/apple-notes-mcp, covering claude.md - apple notes mcp server, related documentation, critical: backslash escaping, why this matters and examples.

sweetrb/apple-notes-mcp · 3,509 tokens

apple-mail-mcp CLAUDE.md

Instructions for sweetrb/apple-mail-mcp, covering claude.md - apple mail mcp server, configuring imap / smtp (when a user asks to set it up), critical: backslash escaping, why this matters and examples.

sweetrb/apple-mail-mcp · 5,071 tokens

che-apple-mail-mcp CLAUDE.md

Claude Code instructions for PsychQuant/che-apple-mail-mcp, covering spectra instructions, use /spectra: skills when, workflow, parked changes and release process.

PsychQuant/che-apple-mail-mcp · 1,090 tokens

pyapple-mcp CLAUDE.md

Instructions for 54yyyu/pyapple-mcp, covering claude.md, development commands, installation and development setup, install in development mode with dev dependencies and run the mcp server directly.

54yyyu/pyapple-mcp · 2,956 tokens

macos-mail-mcp CLAUDE.md

Claude Code instructions for marius-cetanas/macos-mail-mcp, covering claude.md — macos-mail-mcp, project overview, operating layer, tech stack and architecture.

marius-cetanas/macos-mail-mcp · 4,971 tokens

yapping-apple-calendar-mcp AGENTS.md

Instructions for yongzhe-wang/yapping-apple-calendar-mcp, covering claude.md — system instructions, section 1 — base rules, section 2 — my rules (hard; apply to every reply / task), format: code comments mirror the memory evidence convention and worked example (python).

yongzhe-wang/yapping-apple-calendar-mcp · 14,142 tokens