Borrowing it
Nothing to install: this file belongs to CursorTouch/MacOS-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.
curl -O https://raw.githubusercontent.com/CursorTouch/MacOS-MCP/main/CLAUDE.mdgit clone --depth 1 https://github.com/CursorTouch/MacOS-MCPWrote 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.
[](https://agentmods.dev/instructions/cursortouch/macos-mcp/claude-md)<a href="https://agentmods.dev/instructions/cursortouch/macos-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/cursortouch/macos-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.
<a href="https://agentmods.dev/instructions/cursortouch/macos-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/cursortouch/macos-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01096 | $0.01096 |
| Opus 5.5 | $0.00438 | $0.00438 |
| Sonnet 5.5 | $0.00219 | $0.00219 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
MacOS-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.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
macOS-MCP: Project Documentation for Claude
Project Overview
macOS-MCP is a lightweight, open-source MCP (Model Context Protocol) server that enables AI agents to seamlessly integrate with and automate macOS through the Accessibility API. It provides tools for file navigation, application control, UI interaction, browser automation, and system command execution.
Tech Stack
- Language: Python 3.11+
- Package Manager: UV
- Build System: Hatchling
- Code Quality: Ruff (formatter/linter at 100 character line length)
Architecture
The project is organized into modular services:
Entry Point (src/macos_mcp/__main__.py)
- Registers all MCP tools
- Initializes core services
- Manages server lifecycle
Desktop Service (src/macos_mcp/desktop/service.py)
- High-level automation orchestrator
- Handles window management, screenshots, input actions, and clipboard operations
- Coordinates with Tree service for UI discovery
Tree Service (src/macos_mcp/tree/service.py)
- Captures the macOS accessibility tree from active and background windows
- Traverses UI elements and identifies interactive components
- Scans multiple sources concurrently (focused app, dock, menu bar, control center, etc.)
Supporting Modules
- Config modules: Constants for interactive roles, actions, and UI configuration
- Views modules: Data classes for structured representation of desktop and tree state
Key Features
- Native macOS Integration: Uses Accessibility API (
ApplicationServices) for native UI interaction - Vision-Optional: Works with any LLM, no requirement for specialized vision models
- Parallel Scanning: Scans multiple UI sources concurrently for improved performance
- Smart Context Awareness: Detects application state (Launchpad, Control Center, etc.) and adjusts behavior
- Screenshot Annotations: Generates visual references with numbered bounding boxes
Tools Provided
| Tool | Purpose |
|---|---|
Click |
Click at coordinates (left/right/double) |
Type |
Type text, optionally clearing existing text |
Scroll |
Scroll vertically or horizontally |
Move |
Move or drag mouse pointer |
Shortcut |
Press keyboard shortcuts (Cmd+C, etc.) |
Wait |
Pause execution for defined duration |
Snapshot |
Capture desktop state with optional visual annotations |
App |
Launch/manage applications |
Shell |
Execute shell commands or AppleScript |
Scrape |
Extract and convert webpage content to Markdown |
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 · 152 lines · 1,096 tokens per session scan A 03e409b75825
MacOS-MCP CLAUDE.md is an instructions file published in the GitHub repository CursorTouch/MacOS-MCP (237 stars, last pushed 5d ago), licensed MIT. It adds 1,096 tokens to every session, about $0.0044 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 2026-08-30.
MacOS-MCP CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| MacOS-MCP CLAUDE.mdCursorTouch/MacOS-MCP | Instructions file | 237 | 5d ago | MIT | A | 1,096 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 275k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |