unitree_disconnect

THE RISK

Low Risk

Why unitree_disconnect needs a policy

The name suggests terminating a connection to a Unitree robot, which could be a Write or Execute action. However, disconnecting from a robot in motion could be hazardous (leaving it uncontrolled), but it is not clearly destructive, financial, or a direct execution of commands. With no description to confirm behavior, confidence is low.

From the tool's definition Tool name is 'unitree_disconnect'; description is empty and uninformative.

Documented attack patterns abuse exactly the kind of access unitree_disconnect gives an agent:

POLICY

How to control unitree_disconnect

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_disconnect:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "unitree_disconnect": {
      "limits": [
        {
          "counter": "unitree_disconnect_rate",
          "window": "minute",
          "max": 60,
          "scope": "grant"
        }
      ]
    }
  }
}

unitree_disconnect gets a rate cap, and everything else on the server is denied unless you say otherwise.

Create a free account and register Robot — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

SET A RULE FOR THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Robot tools

Destructive dji_disconnect dji_disconnect Execute dji_emergency_stop dji_emergency_stop Execute emergency_stop_all emergency_stop_all Execute run_routine_sequence run_routine_sequence Execute unitree_stop unitree_stop Execute dji_land dji_land Execute dji_perimeter_scan dji_perimeter_scan Execute dji_takeoff dji_takeoff

All 24 Robot tools →

Other tools on other servers

Android Forensics ADB MCP Server generate_app_analysis_report Ethereum Tools add Math MCP Server complex_analysis_suite Crypto_MCP aes_encrypt

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Tool risk categories → How PolicyLayer classifies MCP tools by what they can do.
MCP tool → What an MCP tool is and how clients discover and call it.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about unitree_disconnect

What does the unitree_disconnect tool do? +

unitree_disconnect. It is categorised as a Other tool in the Robot MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on unitree_disconnect? +

Register the Robot MCP server in PolicyLayer and add a rule for unitree_disconnect: 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.

What risk level is unitree_disconnect? +

unitree_disconnect is a Other tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit unitree_disconnect? +

Yes. Add a rate_limit block to the unitree_disconnect 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.

How do I block unitree_disconnect completely? +

Set action: deny in the PolicyLayer policy for unitree_disconnect. 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.

What MCP server provides unitree_disconnect? +

unitree_disconnect 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.

Enforce policy on every Robot tool call.

Start from Robot, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →