AI agents call search_icons 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 retrieves and queries icon metadata from the Lordicon library without side effects. It is a search/lookup operation that returns data only, matching the Read category definition of retrieval operations with no side effects.
From the tool's definition Tool description states it 'Search[es] Lordicon icons by keyword' and 'Returns icon names, families, styles, and indices for use with other tools.' No modification, deletion, execution, or financial transaction occurs.
Attacks that exploit this kind of access
Search Lordicon icons by keyword. Returns icon names, families, styles, and indices for use with other tools. 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 search_icons: 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.
search_icons 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 search_icons 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 search_icons. 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.
search_icons 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 →