AI agents call cortex_get_user_key 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 is a Read operation—it retrieves an existing API key without modifying data. However, severity is high because API keys are sensitive credentials; if an attacker obtains them via this tool, they could impersonate the user and perform unauthorized actions on the system (the requirement for 'superadmin API key' access mitigates the risk somewhat but doesn't change the classification).
From the tool's definition Tool is named 'cortex_get_user_key' and described as 'Get the current API key for a user.' The verb 'Get' indicates retrieval with no data modification.
Attacks that exploit this kind of access
Get the current API key for a user. Requires superadmin API 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_get_user_key: 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_get_user_key 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_get_user_key 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_get_user_key. 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_get_user_key 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 →