AI agents call list_compensations 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 compensation data without modifying it. However, severity is medium rather than low because compensation records are sensitive personal/financial information (salary, bonus details) that, if exposed to an unauthorized agent, could reveal confidential employee compensation structures or be used for social engineering.
From the tool's definition Tool is described as 'List compensation records' and belongs to a 'Read-only MCP server'. The description uses 'List', a query verb with no mutation keywords. It accepts optional filters (personId, typeId) but performs no writes, deletes, or executions.
Attacks that exploit this kind of access
List compensation records (salary, bonus, etc.). Optional filters: personId, typeId. 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_compensations: 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_compensations 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_compensations 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_compensations. 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_compensations 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.
list_compensations is one line of Humaans's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →