AI agents call human_ear_tool to retrieve information from Human without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation: it gathers auditory information from the user's environment through human perception and returns a description. It has no side effects, does not modify data, does not execute code, does not delete anything, and does not involve financial transactions. It is analogous to a query or sensor that retrieves environmental data.
From the tool's definition Tool description states 人間が耳を使って音を聞き、状況を説明します (A human uses their ear to listen to sound and describe the situation). This is a sensory input operation that retrieves information about audio/sounds from the environment.
Documented attack patterns abuse exactly the kind of access human_ear_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_ear_tool:
{
"version": "1",
"default": "deny",
"tools": {
"human_ear_tool": {}
}
}human_ear_tool is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
人間が耳を使って音を聞き、状況を説明します。. It is categorised as a Read tool in the Human MCP Server, which means it retrieves data without modifying state.
Register the Human MCP server in PolicyLayer and add a rule for human_ear_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_ear_tool is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the human_ear_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_ear_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_ear_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.