android_app
AI agents invoke android_app to trigger actions in Android MCP. 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.
The server context mentions 'app management' as a capability. An 'android_app' tool likely installs, launches, stops, or uninstalls applications on an Android device. This spans Execute (launching apps) to Destructive (uninstalling apps). Given the most severe applicable category and the app management context, Execute is selected, but confidence is low due to the empty description.
From the tool's definition Tool name 'android_app' on a server described as enabling 'full Android control' including 'app management'. Description is empty/uninformative.
Attacks that exploit this kind of access
android_app. It is categorised as a Execute tool in the Android MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Android MCP server in PolicyLayer and add a rule for android_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 Android MCP. Nothing to install.
android_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 android_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 android_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.
android_app is provided by the Android MCP server (steph-ux/android-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →