AI agents call get_compensation_type 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 data (a compensation type record) by identifier without modifying, deleting, or executing anything. It is a straightforward read operation on an HRIS system. The read-only nature of the server and the retrieval-only semantics classify this as Read category with low severity, as viewing compensation type definitions poses minimal risk even if accessed by an unauthorized agent.
From the tool's definition Tool name 'get_compensation_type' and description 'Retrieve a single compensation type by id' indicate a retrieval/query operation. Server description explicitly states 'Read-only MCP server' with no side effects.
Attacks that exploit this kind of access
Retrieve a single compensation type by id. 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_compensation_type: 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_compensation_type 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_compensation_type 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_compensation_type. 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_compensation_type 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.
get_compensation_type 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 →