AI agents call preview_icon to retrieve information from Nucleo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves icon preview data from a local database and returns a rendered PNG image. No data is created, modified, deleted, or executed. The operation is purely informational with no capability to alter system state or trigger external actions. This is a straightforward Read operation.
From the tool's definition Tool description states 'Preview a Nucleo icon by ID. Returns the icon as a PNG image.' - a read-only operation that retrieves and displays data without modification, deletion, or external side effects.
Attacks that exploit this kind of access
Preview a Nucleo icon by ID. Returns the icon as a PNG image. It is categorised as a Read tool in the Nucleo MCP Server, which means it retrieves data without modifying state.
Register the Nucleo MCP server in PolicyLayer and add a rule for preview_icon: 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 Nucleo. Nothing to install.
preview_icon 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 preview_icon 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 preview_icon. 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.
preview_icon is provided by the Nucleo MCP server (julianallchin/nucleo-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 →