scan_undo · GTAV-CLAUDE- MCP: Risk & Policy

WHAT IT DOES

What scan_undo does on GTAV-CLAUDE-MCP

AI agents use scan_undo to create or update resources in GTAV-CLAUDE-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GTAV-CLAUDE-MCP environment.

WHY IT NEEDS A POLICY

Why scan_undo needs a policy

This tool reverts/undoes a previous scan operation, restoring state to an earlier point. It modifies state (the current scan/survivor set) but does so reversibly by going back to a prior state. It is a Write-level operation within the game's memory scanning context. Severity is low as it only affects the scan state within a game environment.

From the tool's definition Revert the last scan step (back to the previous survivor set)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

scan_undo Rate-limited

scan_undo stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "scan_undo": {
      "limits": [
        {
          "counter": "scan_undo_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches GTAV-CLAUDE-MCP, so you can run agents against it safely.

FAQ

Questions about scan_undo

What does the scan_undo tool do? +

Revert the last scan step (back to the previous survivor set). It is categorised as a Write tool in the GTAV-CLAUDE-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on scan_undo? +

Register the GTAV-CLAUDE- MCP server in PolicyLayer and add a rule for scan_undo: 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 GTAV-CLAUDE-MCP. Nothing to install.

What risk level is scan_undo? +

scan_undo is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit scan_undo? +

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

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

scan_undo is provided by the GTAV-CLAUDE- MCP server (tabbedscamper/gtav-claude-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.