Scan all text nodes in the selected Figma node
AI agents call scan_text_nodes to retrieve information from Cursor Talk to Figma MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists text node data from a Figma design file with no side effects. It performs a read-only operation analogous to search or list operations. While the server overall includes destructive operations (delete_node, delete_multiple_nodes) and write operations (create_*, update operations), this specific tool is purely informational.
From the tool's definition Tool description states 'Scan all text nodes in the selected Figma node' — a query operation that retrieves text content without modification. The verb 'scan' indicates passive inspection/enumeration of existing data.
Attacks that exploit this kind of access
Scan all text nodes in the selected Figma node. It is categorised as a Read tool in the Cursor Talk to Figma MCP MCP Server, which means it retrieves data without modifying state.
Register the Cursor Talk to Figma MCP server in PolicyLayer and add a rule for scan_text_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 Cursor Talk to Figma MCP. Nothing to install.
scan_text_nodes 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_text_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 scan_text_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.
scan_text_nodes is provided by the Cursor Talk to Figma MCP server (paragdesai1/parag-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 →