AI agents invoke human_hand_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 a human to perform physical actions in the real world via the Streamlit UI intermediary. Physical manipulations can have real-world consequences that vary widely depending on what action is requested, making this an Execute-category tool.
From the tool's definition 人間が手を使って簡単な物理的操作を実行します (Human uses hands to perform simple physical operations)
Documented attack patterns abuse exactly the kind of access human_hand_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_hand_tool:
{
"version": "1",
"default": "deny",
"tools": {
"human_hand_tool": {
"limits": [
{
"counter": "human_hand_tool_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}human_hand_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.
人間が手を使って簡単な物理的操作を実行します。. 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_hand_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_hand_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_hand_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_hand_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_hand_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.