Get new windows/dialogs/toasts detected since the watcher started.
AI agents call get_notifications to retrieve information from Openowl without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and retrieves information about notifications/dialogs that have appeared on the desktop. It has no side effects, does not modify system state, does not execute code or commands, and does not delete or create data. It is a pure read operation that returns existing information to the AI assistant.
From the tool's definition Tool name is 'get_notifications' and description states 'Get new windows/dialogs/toasts detected since the watcher started' — this retrieves notification data without modifying, deleting, or executing any actions.
Documented attack patterns abuse exactly the kind of access get_notifications gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Openowl, and nothing reaches the server without passing your rules. This is the rule we recommend for get_notifications:
{
"version": "1",
"default": "deny",
"tools": {
"get_notifications": {}
}
}get_notifications is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get new windows/dialogs/toasts detected since the watcher started. It is categorised as a Read tool in the Openowl MCP Server, which means it retrieves data without modifying state.
Register the Openowl MCP server in PolicyLayer and add a rule for get_notifications: 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 Openowl. Nothing to install.
get_notifications is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_notifications 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 get_notifications. 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.
get_notifications is provided by the Openowl MCP server (mihir-kanzariya/openowl). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Openowl, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
40 Openowl tools catalogued and risk-classified — across an index of 43,000+ MCP servers.