Ask the human to make a decision between options. Useful when you need human judgment or preference.
AI agents call human_decision to retrieve information from Human-Controlled MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a human operator for a decision or preference and returns their response. It retrieves information (a human judgment) with no direct side effects on systems or data. The human may act on the decision separately, but the tool itself is a read/query operation — analogous to a poll or prompt.
From the tool's definition Ask the human to make a decision between options. Useful when you need human judgment or preference.
Attacks that exploit this kind of access
Ask the human to make a decision between options. Useful when you need human judgment or preference. It is categorised as a Read tool in the Human-Controlled MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Human-Controlled MCP Server MCP server in PolicyLayer and add a rule for human_decision: 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-Controlled MCP Server. Nothing to install.
human_decision 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_decision 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_decision. 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_decision is provided by the Human-Controlled MCP Server MCP server (lardratboy/human_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →