cortex_run_responder · Cortex MCP: Risk & Policy

WHAT IT DOES

What cortex_run_responder does on Cortex

AI agents invoke cortex_run_responder to trigger actions in Cortex. 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_run_responder needs a policy

This tool triggers active response actions with real-world consequences such as blocking IPs, sending emails, and isolating hosts. While labeled DESTRUCTIVE in the description, it fits the Execute category (running external operations with argument-dependent effects), which is the most severe applicable category here since the effects are operational/environmental rather than purely data deletion.

From the tool's definition Execute a responder action... responders perform real-world side effects (blocking IPs, sending mail, isolating hosts). DESTRUCTIVE: real-world side effects

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cortex_run_responder Rate-limited

cortex_run_responder 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_run_responder": {
      "limits": [
        {
          "counter": "cortex_run_responder_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, so you can run agents against it safely.

FAQ

Questions about cortex_run_responder

What does the cortex_run_responder tool do? +

Execute a responder action against a TheHive entity (case, task, artifact, alert). DESTRUCTIVE: responders perform real-world side effects (blocking IPs, sending mail, isolating hosts). Gated behind the CORTEX_ALLOW_DESTRUCTIVE env var AND confirm=true. It is categorised as a Execute tool in the Cortex 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_run_responder? +

Register the Cortex MCP server in PolicyLayer and add a rule for cortex_run_responder: 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.

What risk level is cortex_run_responder? +

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

Can I rate-limit cortex_run_responder? +

Yes. Add a rate_limit block to the cortex_run_responder 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_run_responder completely? +

Set action: deny in the PolicyLayer policy for cortex_run_responder. 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_run_responder? +

cortex_run_responder 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.