AI agents call wp_plugin_search 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 retrieves and displays information from the public WordPress plugin directory without any side effects, state changes, or code execution. It is a straightforward search/query operation fitting the Read category. Severity is low because the blast radius of misuse is minimal — an attacker cannot modify WordPress, execute arbitrary code, or access sensitive data through search results alone.
From the tool's definition Tool description states it 'Search[es] the official wordpress.org plugin directory' and 'Returns top 10 results' — a pure query operation with no modification, deletion, or execution of code. The action is read-only against a public directory.
Attacks that exploit this kind of access
Search the official wordpress.org plugin directory for plugins matching a search term. Returns top 10 results with name, slug, rating, and active install count. 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_plugin_search: 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_search 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_plugin_search 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_search. 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_search 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 →