Send key event to device
AI agents invoke send_key_event to trigger actions in MCP Emulator Controller. 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.
Sending key events causes actions on a remote device (e.g., pressing HOME, BACK, POWER, volume keys, or arbitrary keycodes). This is an external operation execution with side effects that depend on arguments, fitting the Execute category. Misuse could trigger unintended navigation, app launches, or device state changes, warranting medium severity.
From the tool's definition 'Send key event to device' — triggers an external operation (key input) on a connected Android emulator or ADB device
Attacks that exploit this kind of access
Send key event to device. It is categorised as a Execute tool in the MCP Emulator Controller MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Emulator Controller MCP server in PolicyLayer and add a rule for send_key_event: 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 MCP Emulator Controller. Nothing to install.
send_key_event 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 send_key_event 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 send_key_event. 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.
send_key_event is provided by the MCP Emulator Controller MCP server (teemo4621/mcp-emulator-controller). 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 →