{"name": "BEEP", "arguments": {"duration": 1}}
AI agents invoke BEEP to trigger actions in MCP PiShock Server. 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.
BEEP triggers an external operation on a physical PiShock device. It is not purely a data read or write, but an execution of a hardware command. While less harmful than SHOCK, it still causes a real-world physical effect on a device (and potentially on a person wearing it).
From the tool's definition Tool name 'BEEP' on a server that 'Enables controlling PiShock devices (shock, vibrate, beep) via the MCP protocol' — triggers a physical beep action on an external hardware device.
Attacks that exploit this kind of access
{"name": "BEEP", "arguments": {"duration": 1}}. It is categorised as a Execute tool in the MCP PiShock Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP PiShock Server MCP server in PolicyLayer and add a rule for BEEP: 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 PiShock Server. Nothing to install.
BEEP 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 BEEP 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 BEEP. 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.
BEEP is provided by the MCP PiShock Server MCP server (kyrnepi/mcp-pishock-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 →