AI agents invoke unitree_stop to trigger actions in Robot. 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 executes a stop command on a physical Unitree robot, causing real-world motion to cease. This is an Execute action (triggers external hardware operation) rather than Read (no data retrieval) or Write (not creating/modifying persistent data reversibly). It is not Destructive (stop is reversible) nor Financial.
From the tool's definition Tool name 'unitree_stop' on a robot-control server for Unitree robots. Sibling tools include emergency stop and flight control operations (takeoff, land). The '_stop' suffix indicates a command that triggers immediate physical action on hardware.
Documented attack patterns abuse exactly the kind of access unitree_stop gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Robot, and nothing reaches the server without passing your rules. This is the rule we recommend for unitree_stop:
{
"version": "1",
"default": "deny",
"tools": {
"unitree_stop": {
"limits": [
{
"counter": "unitree_stop_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}unitree_stop 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.
unitree_stop. It is categorised as a Execute tool in the Robot MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Robot MCP server in PolicyLayer and add a rule for unitree_stop: 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 Robot. Nothing to install.
unitree_stop 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 unitree_stop 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 unitree_stop. 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.
unitree_stop is provided by the Robot MCP server (showkeyjar/robot-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Robot, 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.
24 Robot tools catalogued and risk-classified — across an index of 43,000+ MCP servers.