AI agents call get_node to retrieve information from Figmad without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward data retrieval operation that queries existing Figma design nodes. It has no side effects, does not modify state, and does not trigger external operations. The blast radius of misuse is minimal—an agent could retrieve sensitive design information but cannot alter or delete it.
From the tool's definition Tool description states it 'Get[s] specific nodes from a Figma file by their IDs' and is 'more efficient than getting the full file'—pure retrieval with no modification, deletion, or execution.
Attacks that exploit this kind of access
Get specific nodes from a Figma file by their IDs. More efficient than getting the full file when you know what nodes you need. It is categorised as a Read tool in the Figmad MCP Server, which means it retrieves data without modifying state.
Register the Figmad MCP server in PolicyLayer and add a rule for get_node: 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 Figmad. Nothing to install.
get_node 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_node 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_node. 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_node is provided by the Figmad MCP server (toro1221/figmad-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 →