library_insert_item · Whiteboard MCP: Risk & Policy

WHAT IT DOES

What library_insert_item does on Whiteboard

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

WHY IT NEEDS A POLICY

Why library_insert_item needs a policy

This tool creates new diagram elements on the canvas and modifies internal references (containerId, boundElements, arrow bindings), which are reversible write operations. It does not execute arbitrary code, delete data irreversibly, or move financial assets. The 'shift' positioning and reference remapping indicate state modification rather than mere read access.

From the tool's definition Tool description explicitly states it will 'Insert a specific item from an Excalidraw library onto the canvas' and 'cloned with fresh element ids' — these are create/modify operations on canvas state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

library_insert_item Rate-limited

library_insert_item 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": {
    "library_insert_item": {
      "limits": [
        {
          "counter": "library_insert_item_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 Whiteboard, so you can run agents against it safely.

FAQ

Questions about library_insert_item

What does the library_insert_item tool do? +

Insert a specific item from an Excalidraw library onto the canvas. Source is one of: libraryUrl / libraryPath / userLibraryName. The item is cloned with fresh element ids and shifted so its bbox top-left aligns with target. Internal references (containerId / boundElements / arrow bindings) are remapped. External references are dropped. It is categorised as a Write tool in the Whiteboard MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on library_insert_item? +

Register the Whiteboard MCP server in PolicyLayer and add a rule for library_insert_item: 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 Whiteboard. Nothing to install.

What risk level is library_insert_item? +

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

Can I rate-limit library_insert_item? +

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

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

library_insert_item is provided by the Whiteboard MCP server (kamiazya/whiteboard). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.