AI agents call unitree_status to retrieve information from Robot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Status tools retrieve current state information from a robot without modifying its behavior or executing commands. The description is empty, but the naming convention and context of sibling tools strongly suggest this queries robot state (battery, position, mode, etc.).
From the tool's definition Tool name 'unitree_status' with suffix '_status' indicates querying state/telemetry of a Unitree robot; sibling tools include other status/query operations (dji_status) and action commands (dji_takeoff, dji_land), establishing the pattern that '_status' tools…
Documented attack patterns abuse exactly the kind of access unitree_status 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_status:
{
"version": "1",
"default": "deny",
"tools": {
"unitree_status": {}
}
}unitree_status is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
unitree_status. It is categorised as a Read tool in the Robot MCP Server, which means it retrieves data without modifying state.
Register the Robot MCP server in PolicyLayer and add a rule for unitree_status: 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_status is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the unitree_status 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_status. 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_status 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.