Perform a swipe gesture between two coordinates
AI agents invoke android_swipe to trigger actions in Android MCP Server. 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 a touch/gesture action on a live Android device. It is not merely reading data, nor does it inherently destroy data or move money, but it triggers external device operations (UI interaction) whose effects depend on the coordinates and context — e.g., swiping to delete, dismiss, or navigate. This places it firmly in Execute.
From the tool's definition 'Perform a swipe gesture between two coordinates' — triggers a physical input action on an Android device via ADB
Attacks that exploit this kind of access
Perform a swipe gesture between two coordinates. It is categorised as a Execute tool in the Android MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Android MCP Server MCP server in PolicyLayer and add a rule for android_swipe: 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 Server. Nothing to install.
android_swipe 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_swipe 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_swipe. 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_swipe is provided by the Android MCP Server MCP server (jduartedj/android-mcp-server). 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 →