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.
git clone --depth 1 https://github.com/supremehyo/appium-mcp-claude-androidWrote 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/mcp/supremehyo/appium-mcp-claude-android/appium)<a href="https://agentmods.dev/mcp/supremehyo/appium-mcp-claude-android/appium"><img src="https://agentmods.dev/badge/mcp/supremehyo/appium-mcp-claude-android/appium/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/mcp/supremehyo/appium-mcp-claude-android/appium"><img src="https://agentmods.dev/badge/mcp/supremehyo/appium-mcp-claude-android/appium.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
appium 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.
What it actually says
{
"appium": {
"type": "stdio",
"command": "python3",
"args": [
"-m",
"mcp_appium.server"
]
}
}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 · 10 lines scan A 052b62ac1574
appium is an MCP server published in the GitHub repository supremehyo/appium-mcp-claude-android (3 stars, last pushed 8mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 2026-08-31.
Other mcp servers, from other repositories
tapp
Autonomous QA for iOS + web — agents get a deterministic ship/no-ship verdict, no test code. Runs locally from the tapp-mcp npm package.
momentic-mobile
MCP server "momentic-mobile" as configured in momentic-ai/skills. Runs locally from the momentic-mobile npm package.
devicecloud
Triage failing DeviceCloud Maestro test runs: fail reasons, screenshots, flaky-flow analytics. Runs locally from the devicecloud-mcp npm package. Needs 1 environment variable to run.
harmonyos-dev-mcp
HarmonyOS MCP service for device automation, app deployment, UI interaction, E2E support, and log validation. Runs locally from the harmonyos-dev-mcp Python package.
appium-mcp
AI-driven mobile test automation framework with Appium MCP server, Page Object Model, and AWS Bedrock integration - Write test automation in natural language with automatic page objects and test generation. Runs locally from the appium-mcp Python package.
mcp
Build, test and run iOS apps on a remote Mac from any machine. XcodeBuildMCP-compatible tools. Runs locally from the @doublespeed/mcp npm package. Needs 1 environment variable to run.