Get an employee
AI agents call get_tshirt_size to retrieve information from Paylocity MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves read-only employee information. While the server manages sensitive data like SSNs and bank accounts, the description explicitly notes automated redaction of sensitive information before reaching the model. T-shirt size is non-sensitive personal data. The action is a simple GET operation with no capability to modify, delete, or execute external operations.
From the tool's definition Tool name is 'get_tshirt_size' and description states 'Get an employee'. This is a retrieval operation that queries employee data (specifically t-shirt size) with no modification or side effects.
Attacks that exploit this kind of access
Get an employee. It is categorised as a Read tool in the Paylocity MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Paylocity MCP Server MCP server in PolicyLayer and add a rule for get_tshirt_size: 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 Paylocity MCP Server. Nothing to install.
get_tshirt_size 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_tshirt_size 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_tshirt_size. 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_tshirt_size is provided by the Paylocity MCP Server MCP server (lucid-drone-technologies/paylocity-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 →