get icons by desc and prefix (LIKE AS ant-design)
AI agents call get_icons_by_desc_and_prefix to retrieve information from PickAPIcon MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and retrieves icon data based on description and prefix filters. It has no side effects, cannot modify data, execute code, or affect system state. The operation is purely informational lookup, consistent with Read category tools like search and fetch.
From the tool's definition Tool retrieves SVG icons via search/query ('get icons by desc and prefix'), with no modification, deletion, or execution capabilities. The description indicates a search operation against the Iconify API to retrieve icon data.
Attacks that exploit this kind of access
get icons by desc and prefix (LIKE AS ant-design). It is categorised as a Read tool in the PickAPIcon MCP MCP Server, which means it retrieves data without modifying state.
Register the PickAPIcon MCP server in PolicyLayer and add a rule for get_icons_by_desc_and_prefix: 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 PickAPIcon MCP. Nothing to install.
get_icons_by_desc_and_prefix 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 get_icons_by_desc_and_prefix 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 get_icons_by_desc_and_prefix. 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.
get_icons_by_desc_and_prefix is provided by the PickAPIcon MCP server (leee62/pickapicon-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 →