manage_scene

Named scene management. action: capture (save current item states), activate (restore a saved scene).

SERVEROpenhab SOURCEdeswong/openhab-mcp

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/deswong-openhab-mcp/manage-scene.md

WHAT IT DOES

What manage_scene does on Openhab

AI agents use manage_scene to create or update resources in Openhab, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Openhab environment.

RISK

Why manage_scene is rated Medium

The capture action saves/creates scene data (Write), and activate modifies the live state of items in the home (Write). While these are reversible (scenes can be overwritten or different scenes activated), they directly alter the operational state of controlled devices. The high severity reflects that misuse could change HVAC settings, locks, lighting, or other critical home systems.

From the tool's definition Tool performs 'capture (save current item states)' and 'activate (restore a saved scene)' — both are state modification operations that persist changes to the home automation system.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs manage_scene safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Openhab, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For manage_scene, this is the rule to start with:

manage_scene Rate-limited

manage_scene stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "manage_scene": {
      "limits": [
        {
          "counter": "manage_scene_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Openhab, apply this rule, and every manage_scene call is checked against it from then on.

FAQ

Questions about manage_scene

What does the manage_scene tool do? +

Named scene management. action: capture (save current item states), activate (restore a saved scene). It is categorised as a Write tool in the Openhab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on manage_scene? +

Register the Openhab MCP server in PolicyLayer and add a rule for manage_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 Openhab. Nothing to install.

What risk level is manage_scene? +

manage_scene is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit manage_scene? +

Yes. Add a rate_limit block to the manage_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 manage_scene completely? +

Set action: deny in the PolicyLayer policy for manage_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 manage_scene? +

manage_scene is provided by the Openhab MCP server (deswong/openhab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Openhab, and thousands of servers like it.

This server

All 25 Openhab tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →