send_command
Send a command (ON, OFF, numeric value, etc.) to a single item.
This record as markdown: /tools/deswong-openhab-mcp/send-command.md
What send_command does on Openhab
AI agents invoke send_command to trigger actions in Openhab. 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 send_command is rated High
Sending commands to OpenHAB items triggers real-world effects on smart home devices (lights, locks, thermostats, switches, etc.). This is an Execute action because it dispatches commands whose effects depend on the target item and value. Misuse could unlock doors, disable alarms, alter HVAC, or trigger unsafe states — hence high severity.
From the tool's definition 'Send a command (ON, OFF, numeric value, etc.) to a single item' — triggers external operations on physical/virtual home automation devices
Attacks that exploit this kind of access
The rule that runs send_command 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 send_command, this is the rule to start with:
send_command 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Openhab, apply this rule, and every send_command call is checked against it from then on.
Questions about send_command
Send a command (ON, OFF, numeric value, etc.) to a single item. It is categorised as a Execute tool in the Openhab MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Openhab MCP server in PolicyLayer and add a rule for send_command: 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.
send_command is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the send_command 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 send_command. 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.
send_command 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