Skip the next occurrence of a schedule rule.
AI agents use skip_schedule to create or update resources in Home Controller — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Home Controller environment.
The tool creates or modifies data (schedule state) reversibly—skipping a schedule is not permanent deletion of the rule itself, just a temporary override of the next execution. This fits the Write category.
From the tool's definition Tool description: 'Skip the next occurrence of a schedule rule.' This modifies the scheduled behavior of a smart home device by skipping one scheduled event, which is a reversible state change.
Attacks that exploit this kind of access
Skip the next occurrence of a schedule rule. It is categorised as a Write tool in the Home Controller MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Home Controller MCP server in PolicyLayer and add a rule for skip_schedule: 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 Home Controller. Nothing to install.
skip_schedule is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the skip_schedule 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 skip_schedule. 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.
skip_schedule is provided by the Home Controller MCP server (winsthuang/home-controller). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →