AI agents invoke swipe to trigger actions in Phantom. 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 performs a gesture action on a mobile device (iOS simulator, Android emulator, or real device). This is a browser/device action that triggers external operations — it physically interacts with the device UI. It fits the Execute category as it runs device actions whose effects depend on arguments (target element, direction, coordinates).
From the tool's definition Tool name 'swipe' and partial description 'Fait un geste de swipe sur l' (performs a swipe gesture on the...) indicating a UI interaction/gesture action on a device
Attacks that exploit this kind of access
Fait un geste de swipe sur l. It is categorised as a Execute tool in the Phantom MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Phantom 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 Phantom. 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 Phantom MCP server (nthimpulse/phantom-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 →