android_interact
AI agents invoke android_interact 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 tool name 'android_interact' strongly implies triggering interactions on an Android device (e.g., touch, input, gestures). Within a server that provides 'full Android control', this is most likely an Execute-category tool that drives external device operations. Description is empty, which lowers confidence. Severity is high given the blast radius of unrestricted device interaction on a real Android device.
From the tool's definition Tool name 'android_interact' within a server described as enabling 'full Android control' including 'touch interaction' and 'system control'; sibling tools suggest broad device manipulation capabilities.
Attacks that exploit this kind of access
android_interact. 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_interact: 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_interact 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_interact 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_interact. 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_interact 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 →