cortex_ask_human · Cortex MCP: Risk & Policy

WHAT IT DOES

What cortex_ask_human does on Cortex MCP

AI agents invoke cortex_ask_human to trigger actions in Cortex MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why cortex_ask_human needs a policy

This tool triggers an external operation (blocking the agent loop and queuing an interaction via an HTTP endpoint) whose effects depend on runtime arguments. It halts execution flow and interacts with an external API, making it Execute category. Severity is high because misuse could deadlock or stall an AI agent indefinitely, or manipulate human-in-the-loop approval flows.

From the tool's definition Force pause, queue a question for human, block until answered via POST /api/human-answer

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cortex_ask_human Rate-limited

cortex_ask_human stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "cortex_ask_human": {
      "limits": [
        {
          "counter": "cortex_ask_human_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Cortex MCP, so you can run agents against it safely.

FAQ

Questions about cortex_ask_human

What does the cortex_ask_human tool do? +

Force pause, queue a question for human, block until answered via POST /api/human-answer. It is categorised as a Execute tool in the Cortex MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on cortex_ask_human? +

Register the Cortex MCP server in PolicyLayer and add a rule for cortex_ask_human: 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 MCP. Nothing to install.

What risk level is cortex_ask_human? +

cortex_ask_human is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit cortex_ask_human? +

Yes. Add a rate_limit block to the cortex_ask_human 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.

How do I block cortex_ask_human completely? +

Set action: deny in the PolicyLayer policy for cortex_ask_human. 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.

What MCP server provides cortex_ask_human? +

cortex_ask_human is provided by the Cortex MCP server (neuralnexustech/cortex-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.