End session animation with goodbye message.
AI agents invoke robot_sleep to trigger actions in Reachy Claude MCP. 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 triggers a physical animation on a robot (or its simulation) to perform an end-session goodbye sequence. It causes an external physical/operational effect on the robot hardware or simulation, making it an Execute-category action. Misuse could disrupt an active session or cause unexpected robot movement, hence medium severity.
From the tool's definition End session animation with goodbye message
Attacks that exploit this kind of access
End session animation with goodbye message. It is categorised as a Execute tool in the Reachy Claude MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Reachy Claude MCP server in PolicyLayer and add a rule for robot_sleep: 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 Reachy Claude MCP. Nothing to install.
robot_sleep 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 robot_sleep 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 robot_sleep. 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.
robot_sleep is provided by the Reachy Claude MCP server (mchardysam/reachy-claude-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 →