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/xuegao-tzx/android-adb-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/mcp/xuegao-tzx/android-adb-mcp/android-adb)<a href="https://agentmods.dev/mcp/xuegao-tzx/android-adb-mcp/android-adb"><img src="https://agentmods.dev/badge/mcp/xuegao-tzx/android-adb-mcp/android-adb/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/xuegao-tzx/android-adb-mcp/android-adb"><img src="https://agentmods.dev/badge/mcp/xuegao-tzx/android-adb-mcp/android-adb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
android-adb 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
{ "android-adb": { "command": "uvx", "args": [ "android-adb" ] } }
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 · 8 lines scan A 6f4332b9aa67
android-adb is an MCP server published in the GitHub repository xuegao-tzx/android-adb-mcp (3 stars, last pushed 6mo ago), licensed Apache-2.0. 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
xcodebuildmcp
XcodeBuildMCP is a Model Context Protocol server that provides tools for Xcode project management, simulator management, and app utilities. Runs locally from the xcodebuildmcp npm package. Needs 1 environment variable to run.
android-sqlite-mcp
A Model Context Protocol (MCP) server to connect AI agents directly to the embedded SQLite/Room databases of your Android applications. Runs locally from the android-sqlite-mcp npm package.
expo-local-docs-mcp
MCP server for Expo documentation - reads local .mdx files for blazing fast performance. Works out of the box with zero configuration. Runs locally from the expo-local-docs-mcp npm package.
mobile-builder-mcp
MCP server "mobile-builder-mcp" as configured in daffy0208/ai-dev-standards. Runs C:\Users\david\OneDrive - Qolcom\AI\AI_Development_Projects\ai-dev-standards\MCP-SERVERS\mobile-builder-mcp\dist\index.js with node.
ulink
Deep linking for iOS, Android & Flutter. Firebase Dynamic Links alternative. Runs locally from the @ulinkly/mcp-server npm package. Needs 1 environment variable to run.
mcp-connect
MCP server for iOS Simulator control and browser automation - unified toolkit for mobile and web testing. Runs locally from the @plaintest/mcp-connect npm package.