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.
npx agentmods add instructions/surendranb/macos-mcp/agents-mdgit clone --depth 1 https://github.com/surendranb/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/surendranb/macos-mcp/agents-md)<a href="https://agentmods.dev/instructions/surendranb/macos-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/surendranb/macos-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.00788 | $0.00788 |
| Opus 5 | $0.00394 | $0.00394 |
| Sonnet 5 | $0.00158 | $0.00158 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade C, and why
macos-mcp AGENTS.md scanned grade C with 2 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 3d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL "https://macos.builditwithai.xyz/install" | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL "https://macos.builditwithai.xyz/install" | bash How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Agent Operating Manual
For AI Agents (Claude Code, Cursor, Codex, Gemini, Antigravity, OpenCode, Aider) connecting to or executing
macos-mcp.
⚡ 1. Fast Install & Client Wiring (Start Here)
In 90% of cases, you just need to install and configure this MCP server for your user:
# 1-Line Universal Auto-Installer (Configures Claude Code, Cursor, Claude Desktop & Antigravity)
curl -fsSL "https://macos.builditwithai.xyz/install" | bash
# Or launch directly via stdio:
npx -y @surendranb/macos-companion-mcp
uvx macos-companion-mcp
Client Config Snippet (mcp.json / claude_desktop_config.json)
{
"mcpServers": {
"macos-companion": {
"command": "npx",
"args": ["-y", "@surendranb/macos-companion-mcp"]
}
}
}
📖 2. What This Repo Is
A native macOS automation MCP server providing system controls for AI agents on Apple Silicon and Intel Macs.
Primary Tools Available:
notify: Dispatch native macOS notifications with title, message, and sound.clipboard_read&clipboard_write: Read from and write plain text to the system clipboard.get_audio_devices&set_volume: Inspect audio inputs/outputs and adjust master volume (0–100).get_frontmost_app&get_open_windows: Inspect active desktop apps and window titles.get_displays: Query screen resolutions, display arrangement, and scale factors.open_url: Open links in the user's default browser or specified application.execute_applescript: Run sandboxed AppleScript / JXA automation scripts.
👤 3. How to Handle the Human (Permissions)
This server requires zero API keys or environment variables. However, macOS requires user permission for automation:
- Notifications: The first time
notifyruns, macOS may ask the user to allow notifications. - Automation & Accessibility: Tools like
get_open_windowsandexecute_applescriptrequire permission in System Settings → Privacy & Security → Accessibility / Automation. - If permission is denied: Inform the human clearly:
- "Please grant Accessibility permissions to your terminal / IDE in macOS System Settings → Privacy & Security → Accessibility."
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.
- 3d ago First seen · 73 lines · 788 tokens per session scan C 4114a8af729a
macos-mcp AGENTS.md is an instructions file published in the GitHub repository surendranb/macos-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 788 tokens to every session, about $0.0039 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
the-bridge CLAUDE.md
Claude Code instructions for KUP-IP/the-bridge, covering project: the bridge (thebridge), architecture, dev commands, key constraints and historical sprint — data-source registry (v3.8.1).
the-bridge AGENTS.md
AGENTS.md instructions for KUP-IP/the-bridge, covering agents.md, project overview, commands, build and debug build (fast iteration).
FluidAudio copilot-instructions.md
Copilot instructions for FluidInference/FluidAudio, covering fluidaudio - agent development guide, build & test commands, architecture, critical rules and code style (swift-format config).
speech-swift AGENTS.md
AGENTS.md instructions for soniqo/speech-swift, covering agent instructions, communication style, workflow, running tests and benchmarks — sequential and memory-aware and git conventions.
codex-provider-sync AGENTS.md
Instructions for Dailin521/codex-provider-sync, covering ai / agent operator guide, vnext architecture baseline, goal, choose the interface and safe operating flow.
liney AGENTS.md
AGENTS.md instructions for everettjf/liney, covering liney repository collaboration guide, 交流语言 / communication language, project overview, repository layout and build and test.