wordpress_get_menu_items
AI agents call wordpress_get_menu_items to retrieve information from WordPress MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get' prefix strongly indicates data retrieval with no side effects. Retrieving menu items is a read-only operation that queries WordPress menu configuration. Even though the description is empty, the function name provides sufficient evidence.
From the tool's definition Tool name 'wordpress_get_menu_items' indicates a retrieval operation ('get'). The description is empty, but the naming convention and sibling tools (which include read operations like 'wordpress_analyze_seo') suggest this retrieves menu structure data without…
Attacks that exploit this kind of access
wordpress_get_menu_items. It is categorised as a Read tool in the WordPress MCP Server MCP Server, which means it retrieves data without modifying state.
Register the WordPress MCP Server MCP server in PolicyLayer and add a rule for wordpress_get_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 WordPress MCP Server. Nothing to install.
wordpress_get_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_get_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_get_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_get_menu_items is provided by the WordPress MCP Server MCP server (tonypepperwidow123-blip/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 →