Phase 2 v0.1 DOM→Figma JSON adapter (cbm/htmltofigma/v0). Reuses htmltoclaude walker then maps to Figma REST node format (FRAME/TEXT/RECTANGLE/VECTOR/GROUP). v0.6.0 SVG outerHTML + GRADIENT_LINEAR/RADIAL + pseudo + max_nodes. v0.7.0 adds paste-HTML inputs (
AI agents call to_figma to retrieve information from Custom Browser without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and converts DOM content from a URL into Figma JSON format. It extracts/transforms data (accessibility tree, design tokens, DOM structure) without creating, modifying, or deleting anything. The output is a JSON representation for Figma, not an actual write to Figma. Severity is medium because it processes arbitrary URLs and extracts detailed page structure, which could expose sensitive UI information.
From the tool's definition DOM→Figma JSON adapter...Reuses htmltoclaude walker then maps to Figma REST node format (FRAME/TEXT/RECTANGLE/VECTOR/GROUP)
Attacks that exploit this kind of access
Phase 2 v0.1 DOM→Figma JSON adapter (cbm/htmltofigma/v0). Reuses htmltoclaude walker then maps to Figma REST node format (FRAME/TEXT/RECTANGLE/VECTOR/GROUP). v0.6.0 SVG outerHTML + GRADIENT_LINEAR/RADIAL + pseudo + max_nodes. v0.7.0 adds paste-HTML inputs (. It is categorised as a Read tool in the Custom Browser MCP Server, which means it retrieves data without modifying state.
Register the Custom Browser MCP server in PolicyLayer and add a rule for to_figma: 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 Custom Browser. Nothing to install.
to_figma 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 to_figma 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 to_figma. 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.
to_figma is provided by the Custom Browser MCP server (theriz78/eclectique-browser-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 →