A mobile-device control skill for iOS Simulators, Android Emulators, and connected iPhone, iPad, and Android devices. It lets an agent interact with an app through taps, typing, swipes, screenshots, installation, and inspection.

Use it to launch apps, navigate screens, enter text, capture screenshots, install apps, and inspect or reproduce issues on mobile devices.

It removes the need to perform these app checks manually on a simulator, emulator, or connected phone. This helps reproduce and verify mobile-app behaviour from the agent.

mobile-mcp — Skill for Claude Code and Codex by gitsoufiane

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.

Any agent

npx skills add gitsoufiane/mobile-simulator-emulator-mcp --skill mobile-mcp

Clone the repo

git clone --depth 1 https://github.com/gitsoufiane/mobile-simulator-emulator-mcp

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gitsoufiane/mobile-simulator-emulator-mcp/mobile-mcp/github.svg)](https://agentmods.dev/skills/gitsoufiane/mobile-simulator-emulator-mcp/mobile-mcp)

Your own site

<a href="https://agentmods.dev/skills/gitsoufiane/mobile-simulator-emulator-mcp/mobile-mcp"><img src="https://agentmods.dev/badge/skills/gitsoufiane/mobile-simulator-emulator-mcp/mobile-mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gitsoufiane/mobile-simulator-emulator-mcp/mobile-mcp"><img src="https://agentmods.dev/badge/skills/gitsoufiane/mobile-simulator-emulator-mcp/mobile-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 135 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,212 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00135	$0.01212
Opus 5.5	$0.00054	$0.00485
Sonnet 5.5	$0.00027	$0.00242
Haiku 4.5	$0.00014	$0.00121

Measured 9d ago against content hash 7daff59de927, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

mobile-mcp scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- The first iOS UI call builds WebDriverAgent for several minutes. Pi and Codex stop a tool call after 60 seconds by default. Set `"timeout": 300` in the Pi `mcp.json` entry. In `~/.codex/config.toml`, add `tool_timeout_

skills/mobile-mcp/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mobile MCP

Follow the mobile server's MCP instructions. When they differ from this file, they win.

Tool names

This file uses bare tool names such as mobile_doctor.

Pi: call tools.mcp__mobile__mobile_doctor({}) inside codemode. Pi shows only one line of the server instructions, so read them once: return (await describeNamespace("mcp__mobile")).instructions. A failed call resolves with isError: true instead of throwing, so check it.
Claude Code: call mcp__mobile__mobile_doctor. The server instructions are already in context.
Codex: call mobile_doctor on the mobile server. Codex reads the server instructions.

Setup

Run setup only when no mobile tools exist. Give the user the command for their agent; do not change their configuration yourself.

pi mcp add mobile -- npx -y --allow-git=root github:gitsoufiane/mobile-simulator-emulator-mcp
claude mcp add --scope user mobile -- npx -y --allow-git=root github:gitsoufiane/mobile-simulator-emulator-mcp
codex mcp add mobile -- npx -y --allow-git=root github:gitsoufiane/mobile-simulator-emulator-mcp

Physical iPhone or iPad: add --env MOBILE_MCP_IOS_TEAM_ID=<Apple team ID> after mobile and before --.
The first iOS UI call builds WebDriverAgent for several minutes. Pi and Codex stop a tool call after 60 seconds by default. Set "timeout": 300 in the Pi mcp.json entry. In ~/.codex/config.toml, add tool_timeout_sec = 300 and startup_timeout_sec = 120 directly under the existing [mcp_servers.mobile] table; the first start also clones and builds the server.

Work loop

mobile_doctor, then mobile_list_devices. Reuse the exact returned id.
mobile_list_apps for bundle IDs and package names. Add includeSystem: true for built-in apps such as Settings. Never guess an app ID.
Read the screen with mobile_list_elements (query finds one element). Use mobile_take_screenshot for visual checks.
Act. Prefer mobile_tap_element by label over mobile_tap by coordinates. Also mobile_swipe, mobile_type_text, and mobile_press_key.
After each action, call mobile_wait_for_element for the expected result (timeoutMs 500 to 60000, default 10000). Use mobile_scroll_to_element for off-screen items. Do not sleep.
On failure, collect mobile_get_logs or mobile_get_crash_logs. They are not available on physical iOS devices.

Read the full file on GitHub · 71 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.

9d ago First seen · 71 lines · 135 tokens per session scan B 7daff59de927

Subscribe to this mod's changes

mobile-mcp is a skill published in the GitHub repository gitsoufiane/mobile-simulator-emulator-mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 135 tokens to every session and 1,212 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-29.

Mobile

mobile-mcp next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mobile-mcpgitsoufiane/mobile-simulator-emulator-mcp	Skill	0	10d ago	MIT	B	135	Claude Code, Codex
orca-emulator-androidstablyai/orca	Skill	117k	yesterday	MIT	A	102	Claude Code, Codex
glance-canonical-layoutsandroid/skills	Skill	10k	yesterday	Apache-2.0	A	56	Claude Code
android-tombstone-symbolicationdotnet/skills	Skill	5.8k	yesterday	MIT	A	176	Claude Code
dogfoodcallstack/agent-device	Skill	5.3k	yesterday	MIT	A	55	Claude Code
winapp-mauimicrosoft/winappCli	Skill	1.4k	yesterday	MIT	A	68	Claude Code
app_remixrome-os/rome	Skill	889	yesterday	MIT	A	50	Claude Code, Codex

mobile-mcp