Search icons from iconfont.cn (single keyword search only)
AI agents call search_icons to retrieve information from Icon without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves icon data from an external service based on a keyword query. It has no side effects—it does not create, modify, delete, or execute operations. The operation is read-only and limited to searching a public icon database. The severity is low because misuse would only retrieve unwanted search results with no adverse consequences.
From the tool's definition The tool 'search_icons' is described as 'Search icons from iconfont.cn (single keyword search only)'. The verb 'Search' indicates a query operation that retrieves data without modifying, deleting, or executing code.
Documented attack patterns abuse exactly the kind of access search_icons gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Icon, and nothing reaches the server without passing your rules. This is the rule we recommend for search_icons:
{
"version": "1",
"default": "deny",
"tools": {
"search_icons": {}
}
}search_icons 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 icons from iconfont.cn (single keyword search only). It is categorised as a Read tool in the Icon MCP Server, which means it retrieves data without modifying state.
Register the Icon 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 Icon. 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 Icon MCP server (liliangshan/mcp-server-icon). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Icon, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 Icon tools catalogued and risk-classified — across an index of 43,000+ MCP servers.