AI agents call wordpress_list_menu_items 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.
This tool retrieves or queries menu item data from WordPress without modifying, creating, or deleting anything. It performs a straightforward read operation on the REST API endpoint. The blast radius of misuse is minimal since listing menu items is non-destructive and typically contains non-sensitive structural information about site navigation.
From the tool's definition Tool name contains 'list' and description states 'List menu items'; the verb 'list' and passive data retrieval ('if the endpoint is available') indicate a query operation with no side effects.
Attacks that exploit this kind of access
List menu items if the WordPress menu-items REST endpoint is available. 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_menu_items: 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_menu_items 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_menu_items 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_menu_items. 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_menu_items 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 →