automation
Automation generation and testing. action: generate_rule (from NL), discover_patterns (temporal correlation), shadow_run (dry-run preview), simulate (predict outcome + rule chains), validate_rule (JS syntax check).
This record as markdown: /tools/deswong-openhab-mcp/automation.md
What automation does on Openhab
AI agents invoke automation 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 automation is rated High
While the tool includes validation and dry-run capabilities, it fundamentally generates and executes automation rules within OpenHAB. Rule generation from natural language and simulation of rule chains constitute code execution whose side effects (triggering device actions, state changes, notifications) are determined by AI-generated content.
From the tool's definition Tool performs 'generate_rule (from NL)', 'shadow_run (dry-run preview)', 'simulate (predict outcome + rule chains)', and 'validate_rule (JS syntax check)' — actions that execute code generation and logic simulation.
Attacks that exploit this kind of access
The rule that runs automation 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 automation, this is the rule to start with:
automation 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 automation call is checked against it from then on.
Questions about automation
Automation generation and testing. action: generate_rule (from NL), discover_patterns (temporal correlation), shadow_run (dry-run preview), simulate (predict outcome + rule chains), validate_rule (JS syntax check). 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 automation: 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.
automation 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 automation 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 automation. 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.
automation 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