// MCP TOOL REFERENCE

FIGMA MCP SERVER TOOLS

15 tools from the Figma MCP Server MCP Server, categorised by risk level.

// ALL 15 FIGMA MCP SERVER TOOLS

READ 8 tools

Read analyze_file Analyze a Figma file structure and extract metadata Read extract_styles Extract design tokens, styles, and design system information Read find_component_usage Find all instances where a component is used Read get_comments Retrieve all comments from a Figma file Read get_component_details Get detailed information about a specific component Read get_file_structure Get hierarchical file structure with customizable depth Read get_node_for_modification Get detailed node information for modification planning Read list_components List all components available in a Figma file

WRITE 6 tools

Write create_comment Create a new comment at a position or node Write export_file_pages Export all pages from a Figma file Write export_multiple_nodes Export multiple nodes in batch Write export_node Export a specific node as PNG, SVG, PDF, or JPG Write resolve_comment Mark a comment as resolved Write update_node_properties Update properties of a design node

DESTRUCTIVE 1 tools

Destructive delete_comment Delete a comment

// RUNNING THIS SERVER

The managed route: connect Figma MCP Server through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y @oabolade-pegasus/figma-mcp-server

// FAQ

How many tools does the Figma MCP Server MCP server have? +

The Figma MCP Server MCP server exposes 15 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on Figma MCP Server tools? +

Route the Figma MCP Server server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Figma MCP Server tools fall into? +

Figma MCP Server tools are categorised as Read (8), Write (6), Destructive (1). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.