Read the currently selected nodes in the active Figma page.
AI agents call figma_get_selection to retrieve information from MC Figma Bridge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves state information (current selection) from the Figma document without modifying, creating, deleting, or executing anything. It is a pure query that poses minimal risk even if misused by an AI agent, as it cannot alter the document or trigger external actions.
From the tool's definition Tool description states 'Read the currently selected nodes' — a read-only query operation with no side effects. The verb 'Read' and 'get' pattern confirm retrieval semantics.
Attacks that exploit this kind of access
Read the currently selected nodes in the active Figma page. It is categorised as a Read tool in the MC Figma Bridge MCP Server, which means it retrieves data without modifying state.
Register the MC Figma Bridge MCP server in PolicyLayer and add a rule for figma_get_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 MC Figma Bridge. Nothing to install.
figma_get_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_get_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_get_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_get_selection is provided by the MC Figma Bridge MCP server (mochammad123/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 →