AI agents call search_people_by_name 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 and searches employee data without any side effects. It queries an existing dataset and returns filtered results. The read-only nature of the server and the purely informational nature of searching people names confirm this is a Read category tool.
From the tool's definition Tool performs 'Case-insensitive substring search' and 'filters client-side' over people data. Server description states 'Read-only MCP server' with tools to 'query people'. No modifications, deletions, or execution of external operations.
Attacks that exploit this kind of access
Case-insensitive substring search over firstName/lastName/preferredName across all people. Pulls the full people list then filters client-side. 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 search_people_by_name: 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.
search_people_by_name 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 search_people_by_name 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 search_people_by_name. 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.
search_people_by_name 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 →