AI agents call list_families 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 performs a straightforward query/listing operation against a static or semi-static set of icon family metadata. It retrieves information without creating, modifying, deleting, or executing anything. The blast radius of misuse is minimal—an agent could only over-query or enumerate data, which poses no security risk to the Lordicon service or user data.
From the tool's definition Tool name is 'list_families' and description states it 'List all Lordicon icon families and their styles with icon counts' — a pure retrieval operation with no data modification or side effects.
Attacks that exploit this kind of access
List all Lordicon icon families and their styles with icon counts. 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 list_families: 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.
list_families 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 list_families 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 list_families. 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.
list_families 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 →