send_notification · MacWright MCP: Risk & Policy

WHAT IT DOES

What send_notification does on MacWright

AI agents invoke send_notification to trigger actions in MacWright. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why send_notification needs a policy

Sending a system notification triggers an external OS-level operation (displaying a banner) rather than merely reading or writing data. It is reversible and low-blast-radius, but it does interact with the OS notification system, making Execute the most appropriate category. Misuse could be used for social engineering (e.g., fake alerts to the user), but the overall severity is low.

From the tool's definition Display a macOS notification banner... alerting the user that a task is complete or needs attention

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_notification Rate-limited

send_notification stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "send_notification": {
      "limits": [
        {
          "counter": "send_notification_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MacWright, so you can run agents against it safely.

FAQ

Questions about send_notification

What does the send_notification tool do? +

Display a macOS notification banner. Useful for alerting the user that a task is complete or needs attention. Requires notifications to be enabled for Script Editor in System Settings > Notifications. No extra installs needed. It is categorised as a Execute tool in the MacWright MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on send_notification? +

Register the MacWright 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 MacWright. Nothing to install.

What risk level is send_notification? +

send_notification is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit send_notification? +

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.

How do I block send_notification completely? +

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.

What MCP server provides send_notification? +

send_notification is provided by the MacWright MCP server (ruchit-p/macwright). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.