send_task_complete_notification

WHAT IT DOES

What send_task_complete_notification does on Claude Code Notification Hooks

AI agents use send_task_complete_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_task_complete_notification needs a policy

This tool creates notifications as a side effect, constituting a Write operation—it generates new data artifacts (notifications) in the user's notification system. While nominally non-destructive and without data deletion, it does modify system state. Severity is low because notifications are benign, user-facing feedback mechanisms with no impact on critical data, finances, or system integrity.

From the tool's definition Tool description explicitly states it 'send[s]' notifications and 'proactively use[s]' this for informing users.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_task_complete_notification Rate-limited

send_task_complete_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_task_complete_notification": {
      "limits": [
        {
          "counter": "send_task_complete_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_task_complete_notification

What does the send_task_complete_notification tool do? +

AUTOMATICALLY send success notifications when any significant task completes successfully. Claude should proactively use this for: builds finishing, tests passing, file operations completing, refactoring done, analysis complete, long operations finishing. Always notify users of completion for better UX. 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_task_complete_notification? +

Register the Claude Code Notification Hooks MCP server in PolicyLayer and add a rule for send_task_complete_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_task_complete_notification? +

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

Can I rate-limit send_task_complete_notification? +

Yes. Add a rate_limit block to the send_task_complete_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_task_complete_notification completely? +

Set action: deny in the PolicyLayer policy for send_task_complete_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_task_complete_notification? +

send_task_complete_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.