Send push notification
AI agents use push_notify to create or update resources in Garza Home MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Garza Home MCP environment.
This tool creates/sends data (a notification) with reversible effects—notifications can be dismissed or deleted, and the action does not destroy data or execute arbitrary code. It is Write rather than Execute because it performs a well-defined, bounded operation (sending a specific notification) rather than running arbitrary commands.
From the tool's definition Tool name 'push_notify' and description 'Send push notification' indicate creation of a new notification message that is persisted and delivered to user devices.
Attacks that exploit this kind of access
Send push notification. It is categorised as a Write tool in the Garza Home MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Garza Home MCP server in PolicyLayer and add a rule for push_notify: 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 Garza Home MCP. Nothing to install.
push_notify 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 push_notify 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 push_notify. 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.
push_notify is provided by the Garza Home MCP server (itsablabla/garza-home-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 →