simulate · Run Iq MCP: Risk & Policy

WHAT IT DOES

What simulate does on Run Iq

AI agents invoke simulate to trigger actions in Run Iq. 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 simulate needs a policy

The tool executes the parametric policy engine multiple times across N scenarios. It is not a passive read of stored data; it actively triggers rule evaluation computations. There is no data modification, deletion, or financial transaction involved, but it does execute domain-specific calculations via a plugin-supported rules engine, placing it in the Execute category.

From the tool's definition 'Evaluates each scenario independently' — runs the policy/rules engine against multiple input scenarios and returns computed results

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

simulate Rate-limited

simulate 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": {
    "simulate": {
      "limits": [
        {
          "counter": "simulate_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 Run Iq, so you can run agents against it safely.

FAQ

Questions about simulate

What does the simulate tool do? +

Compare N scenarios using the same rules. Evaluates each scenario independently and returns side-by-side results for comparison. It is categorised as a Execute tool in the Run Iq MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on simulate? +

Register the Run Iq MCP server in PolicyLayer and add a rule for simulate: 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 Run Iq. Nothing to install.

What risk level is simulate? +

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

Can I rate-limit simulate? +

Yes. Add a rate_limit block to the simulate 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 simulate completely? +

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

simulate is provided by the Run Iq MCP server (run-iq/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.