Medium Risk

resize_canvas

Resize the canvas of a project. Existing pixels are preserved and positioned at the given anchor point.

How to control resize_canvas ↓

What resize_canvas does on Piskel MCP Server

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

Medium Risk

Why resize_canvas needs a policy

Resizing canvas modifies project metadata and pixel positioning but does not delete data (pixels are preserved). This is a reversible Write operation—the user can resize again to undo or revert changes. It does not execute arbitrary operations, destroy data irreversibly, or cause financial impact.

From the tool's definition Tool modifies canvas dimensions and repositions existing pixels ('Existing pixels are preserved and positioned at the given anchor point'), which is a reversible data transformation on the project structure.

Documented attack patterns abuse exactly the kind of access resize_canvas gives an agent:

How to control resize_canvas

PolicyLayer is an MCP gateway — it sits between your AI agents and Piskel MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for resize_canvas:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "resize_canvas": {
      "limits": [
        {
          "counter": "resize_canvas_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

resize_canvas 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.

  1. Create a free account and register Piskel MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about resize_canvas

What does the resize_canvas tool do? +

Resize the canvas of a project. Existing pixels are preserved and positioned at the given anchor point. It is categorised as a Write tool in the Piskel 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 resize_canvas? +

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

What risk level is resize_canvas? +

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

Can I rate-limit resize_canvas? +

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

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

resize_canvas is provided by the Piskel MCP Server MCP server (yafeiaa/piskel-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Piskel MCP Server tool call.

Start from Piskel MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

45 Piskel MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.