nwo_simulate_trajectory · NWO Robotics MCP: Risk & Policy

WHAT IT DOES

What nwo_simulate_trajectory does on NWO Robotics

AI agents invoke nwo_simulate_trajectory to trigger actions in NWO Robotics. 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.

WHY IT NEEDS A POLICY

Why nwo_simulate_trajectory needs a policy

The tool executes a physics simulation (MuJoCo) in the cloud to validate robot trajectories. This constitutes running external computational processes whose effects depend on the provided trajectory arguments. While it is a simulation (not directly actuating hardware), it runs code/simulation on remote infrastructure and its outputs may directly feed into real robot control decisions on this platform.

From the tool's definition Cloud-hosted physics simulation for trajectory validation. High-fidelity MuJoCo simulation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

nwo_simulate_trajectory Rate-limited

nwo_simulate_trajectory 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "nwo_simulate_trajectory": {
      "limits": [
        {
          "counter": "nwo_simulate_trajectory_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches NWO Robotics, so you can run agents against it safely.

FAQ

Questions about nwo_simulate_trajectory

What does the nwo_simulate_trajectory tool do? +

Cloud-hosted physics simulation for trajectory validation. High-fidelity MuJoCo simulation. It is categorised as a Execute tool in the NWO Robotics MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on nwo_simulate_trajectory? +

Register the NWO Robotics MCP server in PolicyLayer and add a rule for nwo_simulate_trajectory: 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 NWO Robotics. Nothing to install.

What risk level is nwo_simulate_trajectory? +

nwo_simulate_trajectory is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit nwo_simulate_trajectory? +

Yes. Add a rate_limit block to the nwo_simulate_trajectory 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 nwo_simulate_trajectory completely? +

Set action: deny in the PolicyLayer policy for nwo_simulate_trajectory. 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 nwo_simulate_trajectory? +

nwo_simulate_trajectory is provided by the NWO Robotics MCP server (redciprianpater/mcp-server-robotics). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.