restore_checkpoint · AI-Canvas MCP Server MCP: Risk & Policy

WHAT IT DOES

What restore_checkpoint does on AI-Canvas MCP Server

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

WHY IT NEEDS A POLICY

Why restore_checkpoint needs a policy

This tool modifies data (the active design document) in a reversible manner. It does not delete checkpoints themselves, nor does it perform irreversible destruction—the user can create new checkpoints and restore to other states. The blast radius is medium because restoring to the wrong checkpoint could lose recent work, but the action is undoable.

From the tool's definition restore_checkpoint restores document state from a checkpoint, which modifies the current document by overwriting its content with a previously saved state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

restore_checkpoint Rate-limited

restore_checkpoint 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": {
    "restore_checkpoint": {
      "limits": [
        {
          "counter": "restore_checkpoint_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 AI-Canvas MCP Server, so you can run agents against it safely.

FAQ

Questions about restore_checkpoint

What does the restore_checkpoint tool do? +

Restore the document state from a specific checkpoint. It is categorised as a Write tool in the AI-Canvas MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on restore_checkpoint? +

Register the AI-Canvas MCP Server MCP server in PolicyLayer and add a rule for restore_checkpoint: 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 AI-Canvas MCP Server. Nothing to install.

What risk level is restore_checkpoint? +

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

Can I rate-limit restore_checkpoint? +

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

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

restore_checkpoint is provided by the AI-Canvas MCP Server MCP server (laoluojuhai/ai-canvas). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.