AI agents use wp_menu_create 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 WordPress navigation menu, which is a write operation that modifies site configuration reversibly. It does not execute arbitrary code, delete data irreversibly, or involve financial transactions. The severity is medium because misconfiguration could affect site usability or introduce unintended navigation paths, but the impact is localized to menu structure and easily correctable.
From the tool's definition Tool name 'wp_menu_create' and description 'Create a new navigation menu' indicate data creation. The action is reversible (menus can be deleted), and the blast radius is limited to site navigation structure.
Attacks that exploit this kind of access
Create a new navigation 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_create: 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_create 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_create 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_create. 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_create 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 →