cortex_auto_heal · Cortex MCP: Risk & Policy

WHAT IT DOES

What cortex_auto_heal does on Cortex MCP

AI agents invoke cortex_auto_heal 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_auto_heal needs a policy

This tool performs automated remediation by detecting and fixing files and running/fixing tests. It executes repair logic whose effects depend on the current state of the codebase. Since it modifies files (Write) and triggers external operations like test execution (Execute), and the scope of changes is broad and hard to predict, Execute is the most accurate category.

From the tool's definition 'Auto-detect and fix broken files, failed tests, and other issues' — actively modifies files and runs tests to remediate issues

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cortex_auto_heal Rate-limited

cortex_auto_heal 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_auto_heal": {
      "limits": [
        {
          "counter": "cortex_auto_heal_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_auto_heal

What does the cortex_auto_heal tool do? +

Auto-detect and fix broken files, failed tests, and other issues. Returns list of healed items. 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_auto_heal? +

Register the Cortex MCP server in PolicyLayer and add a rule for cortex_auto_heal: 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_auto_heal? +

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

Can I rate-limit cortex_auto_heal? +

Yes. Add a rate_limit block to the cortex_auto_heal 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_auto_heal completely? +

Set action: deny in the PolicyLayer policy for cortex_auto_heal. 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_auto_heal? +

cortex_auto_heal 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.