maestro-mcp-tools-instructions

maestro-mcp-tools-instructions is a command for Claude Code from appboypov/pew-pew-plaza-packs. It costs 22 tokens per session (2,073 once invoked), scanned A, original, MIT.

A guide to Maestro MCP tools, which let an AI assistant control mobile devices and run automated app tests through a shared tool interface.

In plain words
What is it for?
Use it to list devices, start iOS or Android devices, launch applications, and run Maestro tests against them.
Why use it?
It explains how to find or start simulators and emulators, launch apps, and perform test actions without guessing the tool calls.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

Good fit Use it to list devices, start iOS or Android devices, launch applications, and run Maestro tests against them.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/appboypov/pew-pew-plaza-packs/maestro-mcp-tools-best-practices
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.

Clone the repo
git clone --depth 1 https://github.com/appboypov/pew-pew-plaza-packs

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 maestro-mcp-tools-instructions

README.md
[![agentmods](https://agentmods.dev/badge/commands/appboypov/pew-pew-plaza-packs/maestro-mcp-tools-best-practices/github.svg)](https://agentmods.dev/commands/appboypov/pew-pew-plaza-packs/maestro-mcp-tools-best-practices)
Your own site
<a href="https://agentmods.dev/commands/appboypov/pew-pew-plaza-packs/maestro-mcp-tools-best-practices"><img src="https://agentmods.dev/badge/commands/appboypov/pew-pew-plaza-packs/maestro-mcp-tools-best-practices/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 maestro-mcp-tools-instructions

Your own site · 80×15
<a href="https://agentmods.dev/commands/appboypov/pew-pew-plaza-packs/maestro-mcp-tools-best-practices"><img src="https://agentmods.dev/badge/commands/appboypov/pew-pew-plaza-packs/maestro-mcp-tools-best-practices.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,073 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00022 $0.02073
Opus 5 $0.00011 $0.01037
Sonnet 5 $0.00004 $0.00415
Haiku 4.5 $0.00002 $0.00207

Measured 9d ago against content hash b31ac2c47dee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

maestro-mcp-tools-instructions 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 9d 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/commands/apply/maestro-mcp-tools-best-practices.md · 401 lines

How it starts

The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instruction Command

When this command is used, acknowledge that you understand these instructions and will follow them throughout the conversation. Then await the user's request.


🔧 Maestro MCP Tools Guide

💡 Complete reference for using Maestro MCP (Model Context Protocol) tools in Claude Code.

Available MCP Tools

The Maestro MCP server provides the following tools for interacting with devices and running tests:

Device Management

list_devices

List all available devices (simulators/emulators) that can be used for automation.

// Usage
mcp__maestro__list_devices({})

// Returns list of devices with:
// - device_id: Unique identifier
// - platform: ios or android
// - name: Device name
// - status: booted, shutdown, etc.
start_device

Start a simulator/emulator and get its device ID.

// Start specific device
mcp__maestro__start_device({
  device_id: "device-uuid"
})

// Start any iOS device
mcp__maestro__start_device({
  platform: "ios"
})

// Start any Android device
mcp__maestro__start_device({
  platform: "android"
})

// Default (iOS)
mcp__maestro__start_device({})

App Control

launch_app

Launch an application on the connected device.

mcp__maestro__launch_app({
  device_id: "device-uuid",
  appId: "com.example.app"
})
stop_app

Stop an application on the connected device.

mcp__maestro__stop_app({
  device_id: "device-uuid",
  appId: "com.example.app"
})

UI Interaction

tap_on

Tap on a UI element by selector or description.

// Tap by text
mcp__maestro__tap_on({
  device_id: "device-uuid",
  text: "Sign In"
})

// Tap by ID
mcp__maestro__tap_on({
  device_id: "device-uuid",
  id: "signin_button"
})

// Tap with multiple criteria
mcp__maestro__tap_on({
  device_id: "device-uuid",
  text: "Submit",
  enabled: true,
  index: 0
})

// Fuzzy text matching (default: true)
mcp__maestro__tap_on({
  device_id: "device-uuid",
  text: "Sign",  // Will match "Sign In"
  use_fuzzy_matching: true
})

Read the full file on GitHub · 401 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. 9d ago First seen · 401 lines · 22 tokens per session scan A b31ac2c47dee

Subscribe to this mod's changes

maestro-mcp-tools-instructions is a command published in the GitHub repository appboypov/pew-pew-plaza-packs (85 stars, last pushed 8mo ago), licensed MIT. It adds 22 tokens to every session and 2,073 once invoked, about $0.0001 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 2026-09-03.

Related

Other commands, from other repositories