android_system
AI agents invoke android_system 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 explicitly mentions 'system control' as a capability. A tool named 'android_system' on such a server most likely exposes system-level operations (settings changes, reboots, permissions, etc.), which constitutes executing privileged system operations. However, the description is empty, so confidence is low.
From the tool's definition Tool name 'android_system' on a server described as enabling 'full Android control... including screen capture, touch interaction, app management, and system control.'
Attacks that exploit this kind of access
android_system. 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_system: 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_system 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_system 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_system. 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_system 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 →