AI agents call cortex_list_users to retrieve information from Cortex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves user information without creating, modifying, or deleting data. However, it returns sensitive information (user accounts across all organizations) accessible only with elevated superadmin credentials, which elevates the severity from low to medium due to the potential privacy and security implications if an AI agent queries this without proper authorization context.
From the tool's definition Tool name 'cortex_list_users' and description 'List all users across organizations' indicates data retrieval with no modification or deletion. The operation is read-only.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
List all users across organizations (requires superadmin API key via CORTEX_SUPERADMIN_KEY). It is categorised as a Read tool in the Cortex MCP Server, which means it retrieves data without modifying state.
Register the Cortex MCP server in PolicyLayer and add a rule for cortex_list_users: 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 Cortex. Nothing to install.
cortex_list_users 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 cortex_list_users 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 cortex_list_users. 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.
cortex_list_users is provided by the Cortex MCP server (solomonneas/cortex-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 →