get_company_employees
AI agents call get_company_employees to retrieve information from LinkedIn 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 employee information from LinkedIn companies—a read operation with no direct data modification or deletion. However, severity is high because mass scraping of employee lists enables privacy violations, social engineering, and corporate reconnaissance at scale. The tool's lack of description reduces confidence slightly from critical to high.
From the tool's definition Tool name 'get_company_employees' indicates data retrieval. Server description emphasizes 'scraping profiles' and 'authenticated browser automation.' The empty tool description prevents full certainty, but the naming pattern aligns with sibling read tools…
Attacks that exploit this kind of access
get_company_employees. It is categorised as a Read tool in the LinkedIn MCP Server MCP Server, which means it retrieves data without modifying state.
Register the LinkedIn MCP Server MCP server in PolicyLayer and add a rule for get_company_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 LinkedIn MCP Server. Nothing to install.
get_company_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_company_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_company_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_company_employees is provided by the LinkedIn MCP Server MCP server (stickerdaniel/linkedin-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.