Add multiple annotations in one request (single snapshot fetch, single commit, single broadcast). Supports optional grid layout for matrix/comparison diagrams. IMPORTANT: box_with_label does NOT auto-wrap long text; the caller must pre-split long lines by passing text as string[] (each element = ...
AI agents use annotate_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.
The annotate_batch tool creates or modifies annotations on a collaborative Excalidraw diagram. This is a reversible Write operation—annotations can be removed or edited later. It does not execute arbitrary code, delete data, move money, or perform destructive operations.
From the tool's definition Tool description states it 'Add multiple annotations' and involves a 'single commit' and 'single broadcast', indicating it creates and modifies diagram content on the shared canvas.
Attacks that exploit this kind of access
Add multiple annotations in one request (single snapshot fetch, single commit, single broadcast). Supports optional grid layout for matrix/comparison diagrams. IMPORTANT: box_with_label does NOT auto-wrap long text; the caller must pre-split long lines by passing text as string[] (each element = 1 line) so the label fits within width/cellW. 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 annotate_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.
annotate_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 annotate_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 annotate_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.
annotate_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 →