AI agents use wp_plugin_install 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.
Installing a plugin writes new code to the WordPress installation. If activated, it runs arbitrary PHP code on the server, which is effectively an Execute-level action. However, the installation itself is a Write operation (placing files). The 'activate immediately' option elevates severity significantly since it can execute arbitrary plugin code.
From the tool's definition Install a WordPress plugin from the official wordpress.org plugin directory. Optionally activate it immediately after installation.
Attacks that exploit this kind of access
Install a WordPress plugin from the official wordpress.org plugin directory. Optionally activate it immediately after installation. 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_plugin_install: 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_plugin_install 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_plugin_install 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_plugin_install. 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_plugin_install 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 →