AI agents use wp_menu_item_add to create or update resources in Wp Cli — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Wp Cli environment.
This tool creates a new menu item (a custom link), which is a Write operation—it modifies site data but does not delete anything irreversibly. An AI agent misusing this could spam menus with malicious links or deface site navigation, affecting user experience and SEO, hence medium severity. The operation is reversible through item deletion. Confidence is high based on clear naming and description.
From the tool's definition Tool name 'wp_menu_item_add' and description 'Add a custom link to a menu' indicate creation of a menu item, which is a reversible modification of WordPress site structure.
Attacks that exploit this kind of access
Add a custom link to a menu. It is categorised as a Write tool in the Wp Cli MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Wp Cli MCP server in PolicyLayer and add a rule for wp_menu_item_add: 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 Wp Cli. Nothing to install.
wp_menu_item_add is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the wp_menu_item_add 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 wp_menu_item_add. 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.
wp_menu_item_add is provided by the Wp Cli MCP server (mvtandas/wp-cli-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 →