Comprehensive WCAG 2.1 accessibility audit. Works via REST API (no plugin needed) when fileKey is provided, or via plugin bridge for the live canvas. Checks: text contrast (1.4.3/1.4.6), non-text contrast (1.4.11), touch targets (2.5.5/2.5.8), alt text (1.1.1), typography & text spacing (1.4.4/1....
AI agents call figma_check_accessibility to retrieve information from Figma Unified without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though figma_check_accessibility only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Comprehensive WCAG 2.1 accessibility audit. Works via REST API (no plugin needed) when fileKey is provided, or via plugin bridge for the live canvas. Checks: text contrast (1.4.3/1.4.6), non-text contrast (1.4.11), touch targets (2.5.5/2.5.8), alt text (1.1.1), typography & text spacing (1.4.4/1.4.12), heading hierarchy (1.3.1), focus indicators (2.4.7), interactive spacing (2.5.8), color-blind safety (1.4.1). Each issue includes WCAG criterion, severity (error/warning), and actionable fix. It is categorised as a Read tool in the Figma Unified MCP Server, which means it retrieves data without modifying state.
Register the Figma Unified MCP server in PolicyLayer and add a rule for figma_check_accessibility: 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 Unified. Nothing to install.
figma_check_accessibility 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 figma_check_accessibility 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_check_accessibility. 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_check_accessibility is provided by the Figma Unified MCP server (sso-ss/figma-unified-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.