get_widgets
AI agents call get_widgets to retrieve information from Figma MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'get_widgets' strongly indicates a retrieval operation that queries widget data from Figma without modification. While the description is empty (lowering confidence slightly), the naming convention and context from related tools confirm this is a Read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'get_widgets' with no descriptive text; 'get' is a read-only retrieval operation. Sibling tools include 'analyze_widget_structure' (read), 'check_connection' (read), and many creation tools (write), placing this in the retrieval category.
Attacks that exploit this kind of access
get_widgets. It is categorised as a Read tool in the Figma MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Figma MCP Server MCP server in PolicyLayer and add a rule for get_widgets: 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 Server. Nothing to install.
get_widgets 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_widgets 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_widgets. 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_widgets is provided by the Figma MCP Server MCP server (sichang824/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 →