send_notification
AI agents use send_notification to create or update resources in Homeassistant — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Homeassistant environment.
Sending notifications creates new messages/alerts in a system, which is a reversible write operation. Severity is medium because unsolicited or spam notifications can degrade user experience and potentially be abused for social engineering or harassment, but the impact is not destructive or financial.
From the tool's definition Tool named 'send_notification' on a Home Assistant control server; no description provided. The name and context indicate this creates/sends notifications to users or devices.
Attacks that exploit this kind of access
send_notification. It is categorised as a Write tool in the Homeassistant MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Homeassistant MCP server in PolicyLayer and add a rule for send_notification: 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 Homeassistant. Nothing to install.
send_notification 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 send_notification 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_notification. 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_notification is provided by the Homeassistant MCP server (robbrad/homeassistant-mcp). 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 →