get_employees
AI agents call get_employees to retrieve information from MCP Employee API Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the tool name and server's CRUD operation set, 'get_employees' is a read operation that queries and returns employee data without modifying or deleting any records. While the description is empty, the naming and context provide sufficient evidence to classify this as a Read category tool with low severity impact.
From the tool's definition Tool name 'get_employees' with context showing CRUD operations (create, read, update, delete) and sibling tools including add_employee, delete_employee, update_employee indicates this retrieves employee records.
Attacks that exploit this kind of access
get_employees. It is categorised as a Read tool in the MCP Employee API Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Employee API Server MCP server in PolicyLayer and add a rule for get_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 MCP Employee API Server. Nothing to install.
get_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 get_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 get_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.
get_employees is provided by the MCP Employee API Server MCP server (josegarayar/mcp_test). 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 →