cortex_log_progress · Cortex MCP: Risk & Policy

WHAT IT DOES

What cortex_log_progress does on Cortex MCP

AI agents use cortex_log_progress 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_log_progress needs a policy

This tool creates or appends a new progress log entry, modifying the agent's memory state reversibly. It has no destructive capability (logs are not deleted), no code execution, and no financial impact. The blast radius is low—a malicious progress log entry would be benign or easily corrected by subsequent logs.

From the tool's definition Tool name 'cortex_log_progress' and description 'Log a completed step' indicate writing/recording progress state to a persistent memory system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cortex_log_progress Rate-limited

cortex_log_progress 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_log_progress": {
      "limits": [
        {
          "counter": "cortex_log_progress_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_log_progress

What does the cortex_log_progress tool do? +

Log a completed step. 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_log_progress? +

Register the Cortex MCP server in PolicyLayer and add a rule for cortex_log_progress: 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_log_progress? +

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

Can I rate-limit cortex_log_progress? +

Yes. Add a rate_limit block to the cortex_log_progress 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_log_progress completely? +

Set action: deny in the PolicyLayer policy for cortex_log_progress. 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_log_progress? +

cortex_log_progress 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.