draw_rectangles

A write tool on the 🪄 ImageSorcery MCP server.

SERVER🪄 ImageSorcery MCP SOURCEsunriseapps/imagesorcery-mcp

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade B, identity unverified Pull the record →

This record as markdown: /tools/sunriseapps-imagesorcery-mcp/draw-rectangles.md

WHAT IT DOES

What draw_rectangles does on 🪄 ImageSorcery MCP

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

RISK

Why draw_rectangles is rated Medium

Drawing rectangles onto an image is a write/modification operation — it creates or alters visual content. Sibling tools (draw_arrows, draw_circles, draw_lines, draw_texts) all follow the same pattern of annotating/modifying images, which is reversible in principle (original can be retained). Empty description lowers confidence.

From the tool's definition Tool name 'draw_rectangles' implies drawing/adding rectangle shapes to an image, which modifies image data. Description is empty, so classification is based on name alone.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs draw_rectangles safely

PolicyLayer is an MCP gateway: it sits between your AI agents and 🪄 ImageSorcery MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For draw_rectangles, this is the rule to start with:

draw_rectangles Rate-limited

draw_rectangles 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": {
    "draw_rectangles": {
      "limits": [
        {
          "counter": "draw_rectangles_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect 🪄 ImageSorcery MCP, apply this rule, and every draw_rectangles call is checked against it from then on.

FAQ

Questions about draw_rectangles

What does the draw_rectangles tool do? +

draw_rectangles is a write tool on the 🪄 ImageSorcery MCP server. It is categorised as a Write tool in the 🪄 ImageSorcery 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 draw_rectangles? +

Register the 🪄 ImageSorcery MCP server in PolicyLayer and add a rule for draw_rectangles: 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 🪄 ImageSorcery MCP. Nothing to install.

What risk level is draw_rectangles? +

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

Can I rate-limit draw_rectangles? +

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

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

draw_rectangles is provided by the 🪄 ImageSorcery MCP server (sunriseapps/imagesorcery-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on 🪄 ImageSorcery, and thousands of servers like it.

This server

All 17 🪄 ImageSorcery tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →