AI agents invoke human_mouth_tool to trigger actions in Human. 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 real-world action — causing a human to verbally speak specified words via the Streamlit UI. It is not merely reading or writing data; it executes a physical/verbal action in the real world. Misuse could cause a human to say harmful, embarrassing, or misleading things, hence medium severity.
From the tool's definition 人間が口を使って指定された言葉を発話します (A human uses their mouth to speak specified words)
Documented attack patterns abuse exactly the kind of access human_mouth_tool gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Human, and nothing reaches the server without passing your rules. This is the rule we recommend for human_mouth_tool:
{
"version": "1",
"default": "deny",
"tools": {
"human_mouth_tool": {
"limits": [
{
"counter": "human_mouth_tool_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}human_mouth_tool 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.
人間が口を使って指定された言葉を発話します。. It is categorised as a Execute tool in the Human MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Human MCP server in PolicyLayer and add a rule for human_mouth_tool: 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 Human. Nothing to install.
human_mouth_tool 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 human_mouth_tool 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 human_mouth_tool. 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.
human_mouth_tool is provided by the Human MCP server (upamune/human-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 7 Human tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
7 Human tools catalogued and risk-classified — across an index of 42,500+ MCP servers.