AI agents call wp_theme_list to retrieve information from Wp Cli without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and returns data about installed WordPress themes (name, status, version, update availability). It has no side effects, makes no changes to the system, and does not execute code or trigger external operations. It is a straightforward read operation with minimal risk if misused by an AI agent.
From the tool's definition Tool name 'wp_theme_list' and description states it 'List[s] all installed WordPress themes' and 'Returns a JSON array' — purely retrieves information about themes without modification, deletion, or execution.
Attacks that exploit this kind of access
List all installed WordPress themes with their name, status (active/inactive), version, and update availability. Returns a JSON array. It is categorised as a Read tool in the Wp Cli MCP Server, which means it retrieves data without modifying state.
Register the Wp Cli MCP server in PolicyLayer and add a rule for wp_theme_list: 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_theme_list 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 wp_theme_list 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_theme_list. 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_theme_list 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 →