cortex_add_decision · Cortex MCP: Risk & Policy

WHAT IT DOES

What cortex_add_decision does on Cortex MCP

AI agents use cortex_add_decision 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_decision needs a policy

This tool creates a new record (an architectural decision) in the cortex system's persistent memory store. This is a reversible write operation—decisions can be logged, updated, or removed without irreversible consequences. It modifies the system state by adding data but does not execute external code, delete data permanently, move money, or trigger external system actions.

From the tool's definition Tool name 'cortex_add_decision' and description 'Log an architectural decision' indicate data creation/recording of a decision artifact in persistent memory.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cortex_add_decision Rate-limited

cortex_add_decision 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_decision": {
      "limits": [
        {
          "counter": "cortex_add_decision_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_decision

What does the cortex_add_decision tool do? +

Log an architectural decision. 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_decision? +

Register the Cortex MCP server in PolicyLayer and add a rule for cortex_add_decision: 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_decision? +

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

Can I rate-limit cortex_add_decision? +

Yes. Add a rate_limit block to the cortex_add_decision 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_decision completely? +

Set action: deny in the PolicyLayer policy for cortex_add_decision. 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_decision? +

cortex_add_decision 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.