AI agents call scan_nodes_by_types to retrieve information from MCP Figma without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or filters existing design elements by their types within a Figma node hierarchy. It has no side effects—it does not create, modify, delete, or execute actions. The operation is purely informational, allowing users to locate and analyze design structure. Low severity because misuse poses minimal risk (worst case: unnecessary information retrieval).
From the tool's definition Tool description states 'Scan for child nodes with specific types' which is a query/search operation. The verb 'scan' indicates information retrieval without modification.
Attacks that exploit this kind of access
Scan for child nodes with specific types in the selected Figma node. It is categorised as a Read tool in the MCP Figma MCP Server, which means it retrieves data without modifying state.
Register the MCP Figma MCP server in PolicyLayer and add a rule for scan_nodes_by_types: 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 MCP Figma. Nothing to install.
scan_nodes_by_types is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the scan_nodes_by_types 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 scan_nodes_by_types. 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.
scan_nodes_by_types is provided by the MCP Figma MCP server (yelowflash09/figma_mcp). 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 →