AI agents invoke start_app 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.
This tool executes an operation on a remote Android device by launching an application. While not destructive (the app can be stopped), it has Execute semantics because it triggers external application behavior whose effects depend on which app is started. An agent could misuse this to launch malicious apps, access sensitive device features, or trigger unwanted operations.
From the tool's definition Tool name 'start_app' with description '启动应用' (start application in Chinese) performs an action that triggers execution on a remote Android device. The server description confirms this enables 'app management' and 'remote control of Android devices via ADB'.
Documented attack patterns abuse exactly the kind of access start_app 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 start_app:
{
"version": "1",
"default": "deny",
"tools": {
"start_app": {
"limits": [
{
"counter": "start_app_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}start_app 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.
启动应用. 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 start_app: 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.
start_app 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 start_app 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 start_app. 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.
start_app 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.