AI agents call get_direct_reports to retrieve information from Humaans without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves organizational data (direct reports for a person) with no side effects. It is a pure read operation against a HRIS system. The read-only nature of the server and the explicit 'reads' verb in the description confirm the Read category. Severity is low because exposure of organizational structure data is a common HR visibility use case with limited risk if misused by an AI agent.
From the tool's definition Tool description states 'List direct reports' and 'Reads the `directReports` array on the person record'. Server is described as 'Read-only MCP server'. No modification, deletion, or execution capability.
Attacks that exploit this kind of access
List direct reports of the given person. Reads the directReports array on the person record. It is categorised as a Read tool in the Humaans MCP Server, which means it retrieves data without modifying state.
Register the Humaans MCP server in PolicyLayer and add a rule for get_direct_reports: 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 Humaans. Nothing to install.
get_direct_reports 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 get_direct_reports 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 get_direct_reports. 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.
get_direct_reports is provided by the Humaans MCP server (ptorsten/humaans-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 →