AI agents use send_toast to create or update resources in MCP Windows — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Windows environment.
Sending notifications creates transient UI elements and modifies system notification state, qualifying as a Write operation (creates data/state reversibly). Severity is medium: while notifications are not destructive, an agent could spam notifications to degrade user experience or use them maliciously for social engineering.
From the tool's definition Tool name 'send_toast' indicates sending Windows toast notifications. Sibling tools include 'notification management' per server description. Toast notifications are messages displayed to the user that modify the notification state/UI.
Documented attack patterns abuse exactly the kind of access send_toast gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Windows, and nothing reaches the server without passing your rules. This is the rule we recommend for send_toast:
{
"version": "1",
"default": "deny",
"tools": {
"send_toast": {
"limits": [
{
"counter": "send_toast_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}send_toast stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
send_toast. It is categorised as a Write tool in the MCP Windows MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Windows MCP server in PolicyLayer and add a rule for send_toast: 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 MCP Windows. Nothing to install.
send_toast 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_toast 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_toast. 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_toast is provided by the MCP Windows MCP server (secretiveshell/mcp-windows). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Windows, 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.
28 MCP Windows tools catalogued and risk-classified — across an index of 43,000+ MCP servers.