Advanced selection management with filtering, search, and hierarchy navigation
AI agents call figma_selection to retrieve information from Figma Mcp Write without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool focuses on managing/reading the current selection, filtering, searching, and navigating the node hierarchy. These are read-oriented operations. However, 'selection management' could imply setting/changing the active selection (a Write action). The description lacks explicit mention of modifying state, so Read is the best fit, but confidence is reduced due to ambiguity.
From the tool's definition 'selection management with filtering, search, and hierarchy navigation' — describes querying and navigating the selection state
Documented attack patterns abuse exactly the kind of access figma_selection gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Figma Mcp Write, and nothing reaches the server without passing your rules. This is the rule we recommend for figma_selection:
{
"version": "1",
"default": "deny",
"tools": {
"figma_selection": {}
}
} figma_selection is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Advanced selection management with filtering, search, and hierarchy navigation. It is categorised as a Read tool in the Figma Mcp Write MCP Server, which means it retrieves data without modifying state.
Register the Figma Mcp Write MCP server in PolicyLayer and add a rule for figma_selection: 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 Write. Nothing to install.
figma_selection 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_selection 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_selection. 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_selection is provided by the Figma Mcp Write MCP server (oo/figma-mcp-write-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Figma Mcp Write, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
24 Figma Mcp Write tools catalogued and risk-classified — across an index of 43,000+ MCP servers.