agentmods.dev

iPhone-mcp CLAUDE.md

Project instructions for blitz-ios-mcp, a tool for controlling iOS simulators and connected iPhones. They describe how to choose a device, inspect its screen, find tappable elements, and perform actions using screen coordinates.

In plain words
What is it for?
Use them when testing iOS apps, inspecting screens, tapping controls, taking screenshots, or automating actions on simulators and physical iPhones.
Why use it?
They provide the required device-selection and screen-checking workflow. This helps prevent actions being sent to the wrong device or to coordinates that do not match the screen.

Instructions file

87 5mo ago A scan 355 tokens original MIT
View the source file blitzdotdev/iPhone-mcp
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/blitzdotdev/iphone-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/blitzdotdev/iPhone-mcp
Per session 355 This file is loaded in full into every session.
When invoked 355 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 $0.00355 $0.00355
Opus 5 $0.00178 $0.00178
Sonnet 5 $0.00071 $0.00071
Haiku 4.5 $0.00036 $0.00036

Measured 2d ago against content hash c47f10249cd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

iPhone-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 · 37 lines

What it actually says

blitz-ios-mcp

MCP server for controlling iOS simulators and physical iPhones.

Workflow

  1. Call get_execution_context first to discover available devices
  2. If target === 'ambiguous', ask the user which device to use
  3. If target === 'device', inform the user about viewer_url so they can see the screen
  4. If target === 'none', tell the user to boot a simulator or connect an iPhone
  5. Pass the returned udid to all subsequent tool calls

Key Patterns

  • Use scan_ui before interacting — it returns interactive elements with tap coordinates
  • Use get_screenshot to visually verify the current screen state
  • Use describe_screen for the full element tree (all types, not just interactive)
  • All coordinates are in device screen points (not pixels)
  • Use device_actions for batching multiple sequential actions
  • Choose the smallest scan_ui region possible for speed

Physical Devices

  • Physical devices require WebDriverAgent (WDA) running on the device
  • Run npx blitz-ios-mcp --setup to install WDA and dependencies
  • The viewer URL shows a live screen stream in the browser
  • The agent cannot see the physical device screen directly — rely on scan_ui and get_screenshot

Coordinate Systems

Common iPhone screen sizes (in points):

  • iPhone 15/16 Pro: 393 x 852
  • iPhone 15/16 Pro Max: 430 x 932
  • iPhone SE: 375 x 667

All coordinates passed to tap/swipe should be in these point values.

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 · 37 lines · 355 tokens per session scan A c47f10249cd9

Subscribe to this mod's changes

iPhone-mcp CLAUDE.md is an instructions file published in the GitHub repository blitzdotdev/iPhone-mcp (87 stars, last pushed 5mo ago), licensed MIT. It adds 355 tokens to every session, about $0.0018 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.

MobileProductivityTesting
Related

Other instructions, from other repositories

Amarok-Hider AGENTS.md

Instructions for deltazefiro/Amarok-Hider, covering amarok, project overview, build, e2e test and agent rules.

deltazefiro/Amarok-Hider · 467 tokens

AppClaw CLAUDE.md

Instructions for appclawhq/AppClaw, covering claude.md, what is appclaw?, build & run commands, architecture and entry point & cli modes (src/index.ts).

appclawhq/AppClaw · 2,529 tokens

MobiAI-Core CLAUDE.md

Instructions for ArisGuimera/MobiAI-Core, covering mobiai — mobile development ai ecosystem, bootstrap and principles.

ArisGuimera/MobiAI-Core · 159 tokens

freetube CLAUDE.md

Instructions for leshkodev/freetube, covering claude.md, 1. what this project is, 2. non-negotiable constraints, 3. tech stack (locked) and 4. project structure.

leshkodev/freetube · 9,979 tokens

ConsultMe CLAUDE.md

Instructions for Tarek-Bohdima/ConsultMe, covering claude.md, project context, common commands, module graph and conventions enforced by tooling.

Tarek-Bohdima/ConsultMe · 3,021 tokens

Plonk AGENTS.md

Instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.

ostapondo/Plonk · 3,557 tokens