Fetch all employees for a company.
AI agents call fetch_employees to retrieve information from mcpPaylocity without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves employee records from a payroll system. While it does not create, modify, or delete data (ruling out Write, Execute, Destructive, and Financial categories), the blast radius is high because employee data is sensitive PII. Unauthorized access or exposure to an AI agent could lead to privacy violations and social engineering risks.
From the tool's definition Tool name 'fetch_employees' and description 'Fetch all employees for a company' indicate data retrieval with no modification or deletion.
Attacks that exploit this kind of access
Fetch all employees for a company. It is categorised as a Read tool in the mcpPaylocity MCP Server, which means it retrieves data without modifying state.
Register the mcpPaylocity MCP server in PolicyLayer and add a rule for fetch_employees: 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 mcpPaylocity. Nothing to install.
fetch_employees 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 fetch_employees 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 fetch_employees. 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.
fetch_employees is provided by the mcpPaylocity MCP server (mz462/mcppaylocity). 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 →