call_tool_auto_preview · Superkit MCP: Risk & Policy

WHAT IT DOES

What call_tool_auto_preview does on Superkit

AI agents invoke call_tool_auto_preview to trigger actions in Superkit. 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.

PARAMETERS

Parameter	Type	Required	Description
`port`	number	—
`action`	string	Yes

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why call_tool_auto_preview needs a policy

This tool executes commands to start, stop, or check the status of a development server. These are Execute-category operations because they trigger external processes and system-level effects that depend on the arguments/parameters provided. While not destructive in itself, misuse could disrupt development workflows or expose the application.

From the tool's definition Tool description states it 'Manages (start/stop/status) the local development server' — starting and stopping a server are executable operations that trigger external processes with real effects on the system state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

call_tool_auto_preview Rate-limited

call_tool_auto_preview 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": {
    "call_tool_auto_preview": {
      "limits": [
        {
          "counter": "call_tool_auto_preview_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 Superkit, so you can run agents against it safely.

FAQ

Questions about call_tool_auto_preview

What does the call_tool_auto_preview tool do? +

Manages (start/stop/status) the local development server for previewing the application. It is categorised as a Execute tool in the Superkit MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does call_tool_auto_preview accept? +

call_tool_auto_preview accepts 2 parameters: port, action. Required: action. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on call_tool_auto_preview? +

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

What risk level is call_tool_auto_preview? +

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

Can I rate-limit call_tool_auto_preview? +

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

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

call_tool_auto_preview is provided by the Superkit MCP server (superkit-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.