get_images
AI agents call get_images 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_images' strongly suggests querying or retrieving image assets from Figma documents without modifying them. No description was available to indicate side effects, but the context of a Figma API integration and the presence of other creation/modification tools (create_frame, create_circle, add_comment) that are clearly differentiated by their names suggests this follows standard naming conventions…
From the tool's definition Tool name 'get_images' indicates retrieval of image data; no description provided to suggest modifications or destructive operations. Naming pattern is consistent with retrieval tools like 'get' which are typically read-only operations.
Attacks that exploit this kind of access
get_images. 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_images: 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_images 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_images 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_images. 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_images 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 →