Add/remove elements from an existing frame without recreating it (frameId stays stable so export_png({frameId}) still targets the same group). All-or-nothing on missing ids. Recomputes frame x/y/width/height from the final member bbox plus padding.
AI agents use update_frame_members 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 performs create/update operations on diagram elements—specifically modifying frame contents and recomputing frame dimensions. While it doesn't delete data or execute arbitrary code, it does alter the diagram state in ways that affect rendering and exports. The 'all-or-nothing' atomicity and computed geometry suggest transactional semantics typical of Write operations.
From the tool's definition The tool "Add/remove elements from an existing frame" directly modifies an existing frame's membership and geometry properties (frameId, x/y/width/height). This is a reversible state change to the diagram structure.
Attacks that exploit this kind of access
Add/remove elements from an existing frame without recreating it (frameId stays stable so export_png({frameId}) still targets the same group). All-or-nothing on missing ids. Recomputes frame x/y/width/height from the final member bbox plus padding. 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 update_frame_members: 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.
update_frame_members 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 update_frame_members 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 update_frame_members. 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.
update_frame_members 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 →