Insert multiple items from the same Excalidraw library onto a canvas in one snapshot/update cycle. Source is one of: libraryUrl / libraryPath / userLibraryName. Each item is cloned with fresh ids, shifted to its target, and may optionally receive batch-level or per-item groupAs labels.
AI agents use library_insert_batch 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.
This tool creates new elements on a shared collaborative canvas by cloning library items and applying transformations (shifting positions, optional grouping). These are reversible write operations—the canvas can be cleared, elements can be deleted, or the action undone. The 'batch' aspect and multi-item insertion increase blast radius slightly, but the operation remains non-destructive.
From the tool's definition Tool performs 'Insert multiple items...onto a canvas' and 'Each item is cloned with fresh ids, shifted to its target', which are create/add operations that modify the canvas state reversibly.
Attacks that exploit this kind of access
Insert multiple items from the same Excalidraw library onto a canvas in one snapshot/update cycle. Source is one of: libraryUrl / libraryPath / userLibraryName. Each item is cloned with fresh ids, shifted to its target, and may optionally receive batch-level or per-item groupAs labels. 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.
Register the Whiteboard MCP server in PolicyLayer and add a rule for library_insert_batch: 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.
library_insert_batch is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the library_insert_batch 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.
Set action: deny in the PolicyLayer policy for library_insert_batch. 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.
library_insert_batch 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →