Search for icon categories by category name using partial matching
AI agents call search_categories to retrieve information from Lucide Icons MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries existing category data without altering state. It is a pure read operation consistent with search and list operations typical of icon library APIs. The 'fuzzy_search_categories' sibling confirms this is a browsing/discovery tool. Severity is low because miscategorizing an icon search has no blast radius.
From the tool's definition Tool 'search_categories' performs a search operation with 'partial matching' on icon categories—a read-only query with no side effects, creation, modification, or deletion of data.
Documented attack patterns abuse exactly the kind of access search_categories gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Lucide Icons MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for search_categories:
{
"version": "1",
"default": "deny",
"tools": {
"search_categories": {}
}
}search_categories is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search for icon categories by category name using partial matching. It is categorised as a Read tool in the Lucide Icons MCP MCP Server, which means it retrieves data without modifying state.
Register the Lucide Icons MCP server in PolicyLayer and add a rule for search_categories: 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 Lucide Icons MCP. Nothing to install.
search_categories 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_categories 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_categories. 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_categories is provided by the Lucide Icons MCP server (seeyangzhi/lucide-icons-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 7 Lucide Icons MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
7 Lucide Icons MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.