cortex_add_feature · Cortex MCP: Risk & Policy

WHAT IT DOES

What cortex_add_feature does on Cortex MCP

AI agents use cortex_add_feature 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_add_feature needs a policy

This tool creates or adds new data to the Cortex system's persistent knowledge base. It is a Write operation because it modifies the agent's memory state in a reversible manner. Severity is medium because misuse could pollute the agent's decision-making context with incorrect features, but the effect is not destructive, financial, or immediately catastrophic.

From the tool's definition Tool is named 'cortex_add_feature' with description 'Add a new feature', indicating creation of new data within the persistent memory/knowledge system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cortex_add_feature Rate-limited

cortex_add_feature 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_add_feature": {
      "limits": [
        {
          "counter": "cortex_add_feature_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_add_feature

What does the cortex_add_feature tool do? +

Add a new feature. 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_add_feature? +

Register the Cortex MCP server in PolicyLayer and add a rule for cortex_add_feature: 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_add_feature? +

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

Can I rate-limit cortex_add_feature? +

Yes. Add a rate_limit block to the cortex_add_feature 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_add_feature completely? +

Set action: deny in the PolicyLayer policy for cortex_add_feature. 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_add_feature? +

cortex_add_feature 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.