send_error_notification · Claude Code Notification Hooks MCP

WHAT IT DOES

What send_error_notification does on Claude Code Notification Hooks

AI agents use send_error_notification to create or update resources in Claude Code Notification Hooks — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Code Notification Hooks environment.

WHY IT NEEDS A POLICY

Why send_error_notification needs a policy

This tool creates transient notifications and triggers sound events on the user's desktop/system. Although notifications are ephemeral and reversible, the action constitutes a write operation that modifies system state. The blast radius is low because notifications do not affect application data, configuration, or user files—they only alert the user.

From the tool's definition Tool modifies system state by sending desktop notifications and triggering system sounds ("send error notifications with error sound"). While not persistent data storage, notifications are written to the notification system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_error_notification Rate-limited

send_error_notification 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "send_error_notification": {
      "limits": [
        {
          "counter": "send_error_notification_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about send_error_notification

What does the send_error_notification tool do? +

AUTOMATICALLY send error notifications with error sound when anything fails. Claude must proactively use this when: compilation fails, tests fail, file operations fail, network requests fail, validation errors occur, bash commands fail. Critical for error awareness - always notify on failures. It is categorised as a Write tool in the Claude Code Notification Hooks MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send_error_notification? +

Register the Claude Code Notification Hooks MCP server in PolicyLayer and add a rule for send_error_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 Claude Code Notification Hooks. Nothing to install.

What risk level is send_error_notification? +

send_error_notification is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit send_error_notification? +

Yes. Add a rate_limit block to the send_error_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_error_notification completely? +

Set action: deny in the PolicyLayer policy for send_error_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_error_notification? +

send_error_notification is provided by the Claude Code Notification Hooks MCP server (nkyy/claude-code-notify-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.