Play a notification sound when a task is completed
AI agents invoke notify_completion to trigger actions in MCP Simple AivisSpeech. 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.
This tool triggers an external operation (playing audio/sound) via the AivisSpeech engine. It has a side effect in the real world (producing audio output) but is non-destructive and low-risk. It falls under Execute because it triggers an external operation whose effect depends on the system state, similar to the sibling 'speak' tool which converts text to speech.
From the tool's definition Play a notification sound when a task is completed
Documented attack patterns abuse exactly the kind of access notify_completion gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Simple AivisSpeech, and nothing reaches the server without passing your rules. This is the rule we recommend for notify_completion:
{
"version": "1",
"default": "deny",
"tools": {
"notify_completion": {
"limits": [
{
"counter": "notify_completion_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}notify_completion 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.
Free to start. No card required.
Play a notification sound when a task is completed. It is categorised as a Execute tool in the MCP Simple AivisSpeech MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Simple AivisSpeech MCP server in PolicyLayer and add a rule for notify_completion: 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 Simple AivisSpeech. Nothing to install.
notify_completion is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the notify_completion 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 notify_completion. 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.
notify_completion is provided by the MCP Simple AivisSpeech MCP server (shinshin86/mcp-simple-aivisspeech). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Simple AivisSpeech, 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.
4 MCP Simple AivisSpeech tools catalogued and risk-classified — across an index of 43,000+ MCP servers.