AI agents invoke dismiss_keyboard 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.
This tool performs an action on an external device (iOS simulator, Android emulator, or real device) by dismissing the software keyboard. It is an interaction/automation action rather than a simple read, write, or destructive operation. The blast radius is low since dismissing a keyboard is a benign UI interaction with no lasting side effects.
From the tool's definition 'Ferme le clavier sur le device actif' (closes the keyboard on the active device) — triggers an external operation on a connected simulator/emulator/device
Attacks that exploit this kind of access
Ferme le clavier sur le device actif (iOS et Android). No-op si pas de clavier visible. À utiliser après un type_text quand le clavier bloque les boutons en bas. 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 dismiss_keyboard: 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.
dismiss_keyboard 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 dismiss_keyboard 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 dismiss_keyboard. 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.
dismiss_keyboard 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 →