manage_thing
Manage things. action: create, update, delete, enable, disable, configure.
This record as markdown: /tools/deswong-openhab-mcp/manage-thing.md
What manage_thing does on Openhab
AI agents call manage_thing to permanently remove resources in Openhab, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why manage_thing is rated Critical
The tool explicitly supports 'delete' as one of its actions, which irreversibly removes things from the OpenHAB configuration. Since the most severe applicable category must be chosen, and delete is irreversible, this classifies as Destructive. Misuse could disable or remove physical device integrations across an entire smart home system, with high blast radius.
From the tool's definition action: create, update, delete, enable, disable, configure
Attacks that exploit this kind of access
The rule that runs manage_thing 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_thing, this is the rule to start with:
manage_thing is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Openhab, apply this rule, and every manage_thing call is checked against it from then on.
Questions about manage_thing
Manage things. action: create, update, delete, enable, disable, configure. It is categorised as a Destructive tool in the Openhab MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Openhab MCP server in PolicyLayer and add a rule for manage_thing: 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.
manage_thing is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the manage_thing 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 manage_thing. 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.
manage_thing 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.
More on Openhab, and thousands of servers like it.
Across the catalogue