Install an APK file on an Android device.
AI agents use install_app to create or update resources in Android Device — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Android Device environment.
Installing an APK modifies the device's installed applications irreversibly in a practical sense, but the operation is theoretically reversible via uninstall. This is a Write operation rather than Destructive because the primary intent is to add/install rather than destroy.
From the tool's definition Tool name 'install_app' and description 'Install an APK file on an Android device' indicates creation/modification of device state by adding software.
Attacks that exploit this kind of access
Install an APK file on an Android device. It is categorised as a Write tool in the Android Device MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Android Device MCP server in PolicyLayer and add a rule for install_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 Device. Nothing to install.
install_app is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the install_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 install_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.
install_app is provided by the Android Device MCP server (prashant1507/android-device-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 →