cortex_resolve_issue · Cortex MCP: Risk & Policy

WHAT IT DOES

What cortex_resolve_issue does on Cortex MCP

AI agents use cortex_resolve_issue 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_resolve_issue needs a policy

The tool modifies data (marks an issue as resolved and stores fix description) but does not permanently delete data or execute arbitrary operations. The blast radius is limited—updating issue resolution status in a memory system is a reversible, low-severity write operation. No financial, destructive, or execution semantics are evident. Classified as Write rather than Read because it changes state.

From the tool's definition Tool name indicates 'resolve' action, description states 'Mark issue resolved' which updates the status of an issue and records a 'fix description'. The context indicates this is a memory/brain system for AI agents.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cortex_resolve_issue Rate-limited

cortex_resolve_issue 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_resolve_issue": {
      "limits": [
        {
          "counter": "cortex_resolve_issue_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_resolve_issue

What does the cortex_resolve_issue tool do? +

Mark issue resolved with fix description. 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_resolve_issue? +

Register the Cortex MCP server in PolicyLayer and add a rule for cortex_resolve_issue: 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_resolve_issue? +

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

Can I rate-limit cortex_resolve_issue? +

Yes. Add a rate_limit block to the cortex_resolve_issue 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_resolve_issue completely? +

Set action: deny in the PolicyLayer policy for cortex_resolve_issue. 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_resolve_issue? +

cortex_resolve_issue 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.