Ask the human to search for information. The human will look up the information and provide their findings.
AI agents call human_search 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 requests information retrieval from a human operator. It is purely informational—the human searches and returns findings with no side effects, data modification, code execution, or destructive capability. The delegation to a human operator does not elevate the risk category; the operation itself is a Read.
From the tool's definition Tool name 'human_search' and description 'Ask the human to search for information. The human will look up the information and provide their findings' indicate a read-only operation that retrieves information without modifying, executing, or deleting data.
Attacks that exploit this kind of access
Ask the human to search for information. The human will look up the information and provide their findings. 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_search: 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_search 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_search 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_search. 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_search 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 →