run_scene · HC3 MCP Server MCP: Risk & Policy

WHAT IT DOES

What run_scene does on HC3 MCP Server

AI agents invoke run_scene to trigger actions in HC3 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.

WHY IT NEEDS A POLICY

Why run_scene needs a policy

This tool triggers external operations (scene execution) whose effects depend on the scene ID argument and the scene's configuration. While scenes are pre-defined and potentially less dangerous than arbitrary code execution, they can cause significant real-world consequences (e.g., unlocking doors, disabling security, triggering sprinklers). The blast radius is high if a compromised agent executes unexpected scenes.

From the tool's definition Tool name 'run_scene' with description 'Execute a scene by ID' indicates execution of pre-defined automation sequences in a smart home system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_scene Rate-limited

run_scene 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": {
    "run_scene": {
      "limits": [
        {
          "counter": "run_scene_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 HC3 MCP Server, so you can run agents against it safely.

FAQ

Questions about run_scene

What does the run_scene tool do? +

Execute a scene by ID. It is categorised as a Execute tool in the HC3 MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_scene? +

Register the HC3 MCP Server MCP server in PolicyLayer and add a rule for run_scene: 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 HC3 MCP Server. Nothing to install.

What risk level is run_scene? +

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

Can I rate-limit run_scene? +

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

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

run_scene is provided by the HC3 MCP Server MCP server (jangabrielsson/hc3_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.