Create, get, update, delete, and duplicate geometric shape nodes. Returns YAML with node properties. Supports specialized operations for each node type: rectangles, ellipses, frames, sections, slices, stars, and polygons.
AI agents call figma_nodes to permanently remove resources in Figma Mcp Write — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool explicitly supports 'delete' operations on Figma nodes, which is irreversible destruction of design elements. Since the most severe applicable category applies, and deletion of nodes cannot be undone (Figma's undo history may not be available to an AI agent acting via Plugin API), this qualifies as Destructive.
From the tool's definition Create, get, update, delete, and duplicate geometric shape nodes
Documented attack patterns abuse exactly the kind of access figma_nodes gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Figma Mcp Write, and nothing reaches the server without passing your rules. This is the rule we recommend for figma_nodes:
{
"version": "1",
"default": "deny",
"hide": [
"figma_nodes"
]
} figma_nodes disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Create, get, update, delete, and duplicate geometric shape nodes. Returns YAML with node properties. Supports specialized operations for each node type: rectangles, ellipses, frames, sections, slices, stars, and polygons. It is categorised as a Destructive tool in the Figma Mcp Write MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Figma Mcp Write MCP server in PolicyLayer and add a rule for figma_nodes: 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 Figma Mcp Write. Nothing to install.
figma_nodes is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the figma_nodes 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 figma_nodes. 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.
figma_nodes is provided by the Figma Mcp Write MCP server (oo/figma-mcp-write-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Figma Mcp Write, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
24 Figma Mcp Write tools catalogued and risk-classified — across an index of 43,000+ MCP servers.