Medium Risk

ungroup_elements

Ungroup a group of elements

How to control ungroup_elements ↓

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

Medium Risk

Ungrouping elements modifies the diagram's organizational structure but does not delete data or trigger external operations. The change is reversible (elements can be re-grouped), placing it in the Write category rather than Destructive. The moderate severity reflects that an agent could disrupt diagram organization, but the blast radius is limited to the diagram's visual/structural integrity within Excalidraw.

From the tool's definition Tool name 'ungroup_elements' and description 'Ungroup a group of elements' indicate modification of diagram structure without irreversible deletion.

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

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

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

ungroup_elements 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 Excalidraw 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.

Go deeper

What does the ungroup_elements tool do? +

Ungroup a group of elements. It is categorised as a Write tool in the Excalidraw 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 ungroup_elements? +

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

What risk level is ungroup_elements? +

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

Can I rate-limit ungroup_elements? +

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

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

ungroup_elements is provided by the Excalidraw MCP Server MCP server (yctimlin/mcp_excalidraw). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Excalidraw MCP Server tool call.

Deterministic rules across all 26 Excalidraw MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

26 Excalidraw MCP Server tools catalogued and risk-classified — across an index of 42,500+ 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.