wizard_step · Artillery MCP Server MCP: Risk & Policy

WHAT IT DOES

What wizard_step does on Artillery MCP Server

AI agents invoke wizard_step to trigger actions in Artillery MCP Server. 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 wizard_step needs a policy

While 'wizard_step' itself does not directly run tests, it advances a stateful wizard that presumably leads to test execution (as evidenced by sibling tools like run_test_from_file, run_saved_config, and run_preset_test). Advancing a wizard step is an Execute action because it triggers conditional logic whose effects depend on user input and prior state.

From the tool's definition Tool advances a wizard state machine 'based on user input', which implies it processes and executes logic that transitions internal state and likely triggers downstream operations like Artillery test configuration or execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

wizard_step Rate-limited

wizard_step 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": {
    "wizard_step": {
      "limits": [
        {
          "counter": "wizard_step_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 Artillery MCP Server, so you can run agents against it safely.

FAQ

Questions about wizard_step

What does the wizard_step tool do? +

Advance the wizard to the next step based on user input. It is categorised as a Execute tool in the Artillery MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on wizard_step? +

Register the Artillery MCP Server MCP server in PolicyLayer and add a rule for wizard_step: 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 Artillery MCP Server. Nothing to install.

What risk level is wizard_step? +

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

Can I rate-limit wizard_step? +

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

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

wizard_step is provided by the Artillery MCP Server MCP server (jch1887/artillery-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.