AI agents invoke notify_test to trigger actions in Claude Voice Notify. 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.
The tool executes a test by invoking an external TTS engine to produce audio output ('reads aloud test successful'). This is an active external operation (audio playback via TTS provider), not merely a read or write of data. Blast radius is low since it only produces a benign test audio notification.
From the tool's definition 「テスト成功」と読み上げる (reads aloud 'test successful') — triggers an external TTS operation/auditory output
Documented attack patterns abuse exactly the kind of access notify_test gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Voice Notify, and nothing reaches the server without passing your rules. This is the rule we recommend for notify_test:
{
"version": "1",
"default": "deny",
"tools": {
"notify_test": {
"limits": [
{
"counter": "notify_test_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}notify_test 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.
音声通知の接続テストを実行する。「テスト成功」と読み上げる。. It is categorised as a Execute tool in the Claude Voice Notify MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Voice Notify MCP server in PolicyLayer and add a rule for notify_test: 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 Voice Notify. Nothing to install.
notify_test 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_test 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_test. 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_test is provided by the Claude Voice Notify MCP server (kubouchiyuya/claude-voice-notify). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Voice Notify, 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.
5 Claude Voice Notify tools catalogued and risk-classified — across an index of 43,000+ MCP servers.