AI agents call list_people 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 only retrieves employee data with optional filters; it does not create, modify, delete, or execute any operations. It is a straightforward read operation on the Humaans HRIS API. The read-only nature of the server and the passive query semantics confirm the Read category.
From the tool's definition Tool description: 'List people (employees). Optional filters: email, locationId, status. Paginated via limit/skip (max 250).' The tool retrieves data with no modification capability—only query and filter operations.
Attacks that exploit this kind of access
List people (employees). Optional filters: email, locationId, status. Paginated via limit/skip (max 250). Note: Humaans has no manager-side filter on this endpoint — use get_direct_reports for that. 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 list_people: 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.
list_people 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 list_people 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 list_people. 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.
list_people 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 →