Play an emotion animation without speaking.
AI agents invoke robot_emotion 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 an external physical operation on a robot (or its simulation) — causing it to perform an animation. This is an Execute-category action because it runs a physical/external operation whose effect depends on the argument (which emotion to play). It does not merely read data, nor does it irreversibly destroy anything, but it does actuate a real or simulated robot.
From the tool's definition Play an emotion animation without speaking
Attacks that exploit this kind of access
Play an emotion animation without speaking. 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_emotion: 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_emotion 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_emotion 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_emotion. 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_emotion 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 →