Update an existing Home Assistant automation
AI agents use update_automation to create or update resources in Home Assistant MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Home Assistant MCP Server environment.
This tool creates or modifies data reversibly (Write category). While it doesn't delete automations (which would be Destructive), updating automation rules could alter critical home control logic, potentially affecting security or device behavior.
From the tool's definition Tool description states 'Update an existing Home Assistant automation'. The tool modifies automation configurations, which are data structures that control smart home behavior and device actions.
Attacks that exploit this kind of access
Update an existing Home Assistant automation. It is categorised as a Write tool in the Home Assistant MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Home Assistant MCP Server MCP server in PolicyLayer and add a rule for update_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 Home Assistant MCP Server. Nothing to install.
update_automation 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 update_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 update_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.
update_automation is provided by the Home Assistant MCP Server MCP server (mjrestivo16/mcp-homeassistant). 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 →