AI agents call cortex_wait_and_get_report 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 waits for an already-submitted job to finish and then fetches the resulting report. It is a read/query operation (polling + get). However, severity is medium because it operates in a security investigation/active-response context where misuse (e.g., waiting on a malicious job) could be a step in a larger attack chain, though the tool itself only reads data.
From the tool's definition 'Wait for a job to complete and return the full report' — the tool polls and retrieves a report, no data modification or execution of new actions implied.
Attacks that exploit this kind of access
Wait for a job to complete and return the full report (with polling timeout). 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_wait_and_get_report: 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_wait_and_get_report 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_wait_and_get_report 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_wait_and_get_report. 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_wait_and_get_report 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 →