AI agents invoke move_head to trigger actions in Reachy Mini MCP 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.
The tool almost certainly triggers physical movement of a robot's head in the real world. This is an Execute-category action because it causes an external physical operation. The description is empty, so confidence is reduced, but context from the server and sibling tools strongly implies physical actuation.
From the tool's definition Tool name 'move_head' on a server that controls physical Reachy Mini robots; server description mentions 'head movement' as a core capability
Documented attack patterns abuse exactly the kind of access move_head gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Reachy Mini MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for move_head:
{
"version": "1",
"default": "deny",
"tools": {
"move_head": {
"limits": [
{
"counter": "move_head_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}move_head stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
move_head. It is categorised as a Execute tool in the Reachy Mini MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Reachy Mini MCP Server MCP server in PolicyLayer and add a rule for move_head: 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 Mini MCP Server. Nothing to install.
move_head 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 move_head 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 move_head. 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.
move_head is provided by the Reachy Mini MCP Server MCP server (pixelml/reachy-mini-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Reachy Mini MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Reachy Mini MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.