AI agents invoke adb_swipe to trigger actions in LocalAnt. 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 UI interaction (swipe gesture) on an Android device through ADB. It is an external operation that causes real device input, placing it in the Execute category. Misuse could trigger unintended navigation, dismiss dialogs, or interact with sensitive UI elements, but its blast radius is moderate since it is limited to gesture input on the connected device.
From the tool's definition 'Swipe between coordinates' — triggers a physical touch/gesture action on a connected Android device via ADB
Attacks that exploit this kind of access
Swipe between coordinates. It is categorised as a Execute tool in the LocalAnt MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the LocalAnt MCP server in PolicyLayer and add a rule for adb_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 LocalAnt. Nothing to install.
adb_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 adb_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 adb_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.
adb_swipe is provided by the LocalAnt MCP server (yuga-hashimoto/localant). 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 →