Add annotation (arrow, text, rectangle, highlight, box_with_label) to the whiteboard canvas. box_with_label is a composite of rectangle + centered text label (requires text/title and width; height is optional and defaults to auto-fit). IMPORTANT: box_with_label does NOT auto-wrap long text; the c...
AI agents use annotate 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 modifies the Excalidraw diagram by adding visual elements, but these changes are fully reversible (annotations can be deleted or edited). There is no data deletion, execution of arbitrary code, financial impact, or irreversible destruction. It fits the Write category: creates or modifies data reversibly.
From the tool's definition The tool adds annotations to a whiteboard canvas (arrow, text, rectangle, highlight, box_with_label), which creates or modifies data reversibly. The description explicitly states it performs annotation operations that alter the canvas state.
Attacks that exploit this kind of access
Add annotation (arrow, text, rectangle, highlight, box_with_label) to the whiteboard canvas. box_with_label is a composite of rectangle + centered text label (requires text/title and width; height is optional and defaults to auto-fit). 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. 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: 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 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 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. 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 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 →