AI agents call get_icon_preview to retrieve information from Lordicon without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves visual data about icons without modifying, creating, deleting, or executing anything. It is a straightforward data retrieval operation with no capability to alter state, execute code, or produce external effects. The low severity reflects minimal risk even if misused by an agent.
From the tool's definition Tool performs a retrieval operation ('Get a visual preview') that returns data (SVG image) with no side effects. The description explicitly states it 'Returns the icon as an embedded SVG image' — a read-only query.
Attacks that exploit this kind of access
Get a visual preview of a specific Lordicon icon. Returns the icon as an embedded SVG image. It is categorised as a Read tool in the Lordicon MCP Server, which means it retrieves data without modifying state.
Register the Lordicon MCP server in PolicyLayer and add a rule for get_icon_preview: 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 Lordicon. Nothing to install.
get_icon_preview 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_icon_preview 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_icon_preview. 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_icon_preview is provided by the Lordicon MCP server (roandegraaf/lordicon-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 →