AI agents invoke install_apk to trigger actions in Adb. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Installing an APK triggers execution of an installer process on the Android device and permanently adds a new application. It is an external operation with significant side effects (new app with permissions running on device). While not purely destructive, it goes beyond a simple write — it deploys and registers executable code.
From the tool's definition install_apk / 安装APK文件 — installs an APK file onto the device
Documented attack patterns abuse exactly the kind of access install_apk gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Adb, and nothing reaches the server without passing your rules. This is the rule we recommend for install_apk:
{
"version": "1",
"default": "deny",
"tools": {
"install_apk": {
"limits": [
{
"counter": "install_apk_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}install_apk stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
安装APK文件. It is categorised as a Execute tool in the Adb MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Adb MCP server in PolicyLayer and add a rule for install_apk: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Adb. Nothing to install.
install_apk is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the install_apk rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for install_apk. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
install_apk is provided by the Adb MCP server (wolfcoming/adb_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Adb, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
48 Adb tools catalogued and risk-classified — across an index of 43,000+ MCP servers.