run_steps · MCP4DRL MCP: Risk & Policy

WHAT IT DOES

What run_steps does on MCP4DRL

AI agents invoke run_steps to trigger actions in MCP4DRL. 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 run_steps needs a policy

The tool runs simulation steps as part of a reinforcement learning agent controlling business process resource allocation. This is an Execute action because it triggers external operations (simulation progression) whose effects depend on model state and arguments, with potential business impact on resource allocation decisions.

From the tool's definition Tool name 'run_steps' in context of 'simulation control' and sibling tools like 'step_simulation', 'run_episode', 'reset_simulation' indicate this executes external operations (reinforcement learning simulation steps).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_steps Rate-limited

run_steps 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": {
    "run_steps": {
      "limits": [
        {
          "counter": "run_steps_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 MCP4DRL, so you can run agents against it safely.

FAQ

Questions about run_steps

What does the run_steps tool do? +

run_steps. It is categorised as a Execute tool in the MCP4DRL MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_steps? +

Register the MCP4DRL MCP server in PolicyLayer and add a rule for run_steps: 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 MCP4DRL. Nothing to install.

What risk level is run_steps? +

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

Can I rate-limit run_steps? +

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

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

run_steps is provided by the MCP4DRL MCP server (mostapow/mcp4drl). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.