Swipe from (x1,y1) to (x2,y2) in points. Get coordinates from query_selector. For scrolling and drawers.
AI agents invoke swipe to trigger actions in React Native. 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 swipe tool triggers a UI interaction (a gesture) on a device or emulator, which is an external operation that can navigate screens, open drawers, trigger actions, or scroll content. This falls under Execute as it performs a browser/app action whose effects depend on arguments (coordinates and direction). Misuse could navigate to unintended screens or trigger unintended UI actions, giving it medium severity.
From the tool's definition Swipe from (x1,y1) to (x2,y2) in points... For scrolling and drawers.
Attacks that exploit this kind of access
Swipe from (x1,y1) to (x2,y2) in points. Get coordinates from query_selector. For scrolling and drawers. It is categorised as a Execute tool in the React Native MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the React Native MCP server in PolicyLayer and add a rule for 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 React Native. Nothing to install.
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 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 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.
swipe is provided by the React Native MCP server (@ohah/react-native-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 →