cortex_run_analyzer · Cortex MCP: Risk & Policy

WHAT IT DOES

What cortex_run_analyzer does on Cortex

AI agents invoke cortex_run_analyzer to trigger actions in Cortex. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why cortex_run_analyzer needs a policy

This tool executes an external analyzer on user-supplied data. An AI agent could misuse it by analyzing untrusted observables or triggering expensive/noisy analyses repeatedly. The blast radius includes resource consumption, potential exposure of analysis results, and triggering cascading security events.

From the tool's definition The tool submits an observable to a specific analyzer for analysis. 'Submit' and 'analyzer' indicate execution of external analytical operations whose outcomes depend on the observable type and analyzer parameters.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cortex_run_analyzer Rate-limited

cortex_run_analyzer stays usable, but rate-capped — a runaway agent can't fire it dozens of times 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_run_analyzer": {
      "limits": [
        {
          "counter": "cortex_run_analyzer_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-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, so you can run agents against it safely.

FAQ

Questions about cortex_run_analyzer

What does the cortex_run_analyzer tool do? +

Submit an observable to a specific analyzer for analysis. It is categorised as a Execute tool in the Cortex MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on cortex_run_analyzer? +

Register the Cortex MCP server in PolicyLayer and add a rule for cortex_run_analyzer: 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. Nothing to install.

What risk level is cortex_run_analyzer? +

cortex_run_analyzer is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit cortex_run_analyzer? +

Yes. Add a rate_limit block to the cortex_run_analyzer 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_run_analyzer completely? +

Set action: deny in the PolicyLayer policy for cortex_run_analyzer. 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_run_analyzer? +

cortex_run_analyzer is provided by the Cortex MCP server (solomonneas/cortex-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.