AI agents call wordpress_list_icons to retrieve information from ItchWPMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves metadata about available WordPress icons from a registry. It performs a read-only query operation with no capability to modify, delete, or execute code. The data returned (icon names, categories, SVG markup) is static reference information. The blast radius of misuse is negligible, as an AI cannot harm systems by listing available icons.
From the tool's definition Tool description explicitly states 'List registered SVG icons' and 'Returns icon names, categories, and SVG source'—these are query/retrieval operations with no side effects.
Attacks that exploit this kind of access
List registered SVG icons from the WordPress Icon Registry, introduced in WordPress 7.0. Returns icon names, categories, and SVG source. It is categorised as a Read tool in the ItchWPMCP MCP Server, which means it retrieves data without modifying state.
Register the ItchWP MCP server in PolicyLayer and add a rule for wordpress_list_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 ItchWPMCP. Nothing to install.
wordpress_list_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 wordpress_list_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 wordpress_list_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.
wordpress_list_icons is provided by the ItchWP MCP server (manofsadness/itchwpmcp). 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 →