Get published styles (colors, text styles) from a Figma file
AI agents call get_styles to retrieve information from Figma MCP Proxy Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves existing design data without creating, modifying, deleting, or executing operations. It falls squarely into the Read category with low severity because it provides access to design metadata that is already published and typically non-sensitive in a design system context.
From the tool's definition Tool retrieves published styles (colors, text styles) from a Figma file—a query operation with no modification or deletion. The description uses 'get' and lists read-only design assets (colors, text styles).
Attacks that exploit this kind of access
Get published styles (colors, text styles) from a Figma file. It is categorised as a Read tool in the Figma MCP Proxy Server MCP Server, which means it retrieves data without modifying state.
Register the Figma MCP Proxy Server MCP server in PolicyLayer and add a rule for get_styles: 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 Proxy Server. Nothing to install.
get_styles 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 get_styles 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 get_styles. 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.
get_styles is provided by the Figma MCP Proxy Server MCP server (vbrail/proxy_mcp_figma). 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 →