cortex_confirm_destructive · Cortex MCP: Risk & Policy

WHAT IT DOES

What cortex_confirm_destructive does on Cortex MCP

AI agents invoke cortex_confirm_destructive 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_confirm_destructive needs a policy

This tool intercepts and gates potentially destructive operations by prompting for human confirmation. It does not itself destroy data, but it triggers an external interaction (UI modal or terminal prompt) that controls whether a dangerous downstream action proceeds. The most accurate category is Execute, as it orchestrates an external operation (confirmation gate/UI action) whose effect depends on the response.

From the tool's definition Block dangerous actions until human confirms. Shows red modal in dashboard. Falls back to terminal if no dashboard.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cortex_confirm_destructive Rate-limited

cortex_confirm_destructive 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_confirm_destructive": {
      "limits": [
        {
          "counter": "cortex_confirm_destructive_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_confirm_destructive

What does the cortex_confirm_destructive tool do? +

Block dangerous actions until human confirms. Shows red modal in dashboard. Falls back to terminal if no dashboard. 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_confirm_destructive? +

Register the Cortex MCP server in PolicyLayer and add a rule for cortex_confirm_destructive: 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_confirm_destructive? +

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

Can I rate-limit cortex_confirm_destructive? +

Yes. Add a rate_limit block to the cortex_confirm_destructive 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_confirm_destructive completely? +

Set action: deny in the PolicyLayer policy for cortex_confirm_destructive. 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_confirm_destructive? +

cortex_confirm_destructive 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.