AI agents use cortex_create_user to create or update resources in Cortex — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cortex environment.
This tool creates new user accounts, which is a reversible Write operation that modifies organizational data (user roster). While not destructive or financial, creating unauthorized users could grant malicious actors persistent access to the Cortex platform and its security analysis capabilities.
From the tool's definition Tool name 'cortex_create_user' and description 'Create a new user in an organization' explicitly indicates creation of a new account/user record. Requires 'superadmin API key', indicating privileged administrative access.
Attacks that exploit this kind of access
Create a new user in an organization (requires superadmin API key). It is categorised as a Write tool in the Cortex MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cortex MCP server in PolicyLayer and add a rule for cortex_create_user: 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_create_user is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the cortex_create_user 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_create_user. 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_create_user 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 →