history_redo · SVG Canvas MCP: Risk & Policy

WHAT IT DOES

What history_redo does on SVG Canvas MCP

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

WHY IT NEEDS A POLICY

Why history_redo needs a policy

This tool modifies SVG canvas state by reapplying previously undone operations. It is reversible (can be undone again) and has no external side effects, destructive actions, code execution, or financial implications. It falls under Write category as it changes the canvas content in a non-destructive way.

From the tool's definition Tool name 'history_redo' and description (in Korean) '취소한 작업을 다시 실행합니다' which translates to 'Re-executes a cancelled/undone action.' This is a redo operation that reverses an undo, modifying the canvas state by reapplying a previously undone action.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

history_redo Rate-limited

history_redo 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": {
    "history_redo": {
      "limits": [
        {
          "counter": "history_redo_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 SVG Canvas MCP, so you can run agents against it safely.

FAQ

Questions about history_redo

What does the history_redo tool do? +

취소한 작업을 다시 실행합니다. It is categorised as a Write tool in the SVG Canvas 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 history_redo? +

Register the SVG Canvas MCP server in PolicyLayer and add a rule for history_redo: 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 SVG Canvas MCP. Nothing to install.

What risk level is history_redo? +

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

Can I rate-limit history_redo? +

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

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

history_redo is provided by the SVG Canvas MCP server (kim62210/svg-canvas-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.