cortex_init · Cortex MCP: Risk & Policy

WHAT IT DOES

What cortex_init does on Cortex MCP

AI agents use cortex_init to create or update resources in Cortex MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cortex MCP environment.

WHY IT NEEDS A POLICY

Why cortex_init needs a policy

This tool creates new project state in Cortex's persistent storage system. While not destructive (reversible) or immediately dangerous compared to Execute or Financial tools, it modifies the knowledge base/memory that subsequent tool calls may depend upon.

From the tool's definition Tool name 'cortex_init' and description 'Initialize Cortex project' indicate creation/setup of a new project structure. This is a write operation that creates persistent state in a 'memory' system (per server description), though it is reversible.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cortex_init Rate-limited

cortex_init stays usable, but capped — an agent stuck in a loop can't make hundreds of changes 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_init": {
      "limits": [
        {
          "counter": "cortex_init_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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_init

What does the cortex_init tool do? +

Initialize Cortex project. You MUST ask the human ALL 10 onboarding questions FIRST using cortex_ask_human. It is categorised as a Write tool in the Cortex MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on cortex_init? +

Register the Cortex MCP server in PolicyLayer and add a rule for cortex_init: 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_init? +

cortex_init is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit cortex_init? +

Yes. Add a rate_limit block to the cortex_init 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_init completely? +

Set action: deny in the PolicyLayer policy for cortex_init. 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_init? +

cortex_init 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.