AI agents call human_taste_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.
The human_taste_tool enables an AI to request human sensory input about food taste and receive descriptive feedback. This is purely informational—the human tastes food and reports observations. There are no side effects, data modifications, code execution, deletions, or financial transactions involved. The classification is Read because it retrieves sensory data through human perception.
From the tool's definition The tool description translates to: 'Humans use their mouth to taste food and describe the taste.' This is a sensory perception and reporting function that retrieves information (taste descriptions) without modifying, executing external operations, destroying…
Documented attack patterns abuse exactly the kind of access human_taste_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_taste_tool:
{
"version": "1",
"default": "deny",
"tools": {
"human_taste_tool": {}
}
}human_taste_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.
人間が口を使って食べ物を味わい、その味を説明します。. 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_taste_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_taste_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_taste_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_taste_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_taste_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.