Compare a local plugin with a WordPress.org plugin
AI agents call compare_plugins to retrieve information from WordPress Plugin Directory MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Comparing plugins involves reading and analyzing plugin metadata and file contents to identify differences. This is fundamentally a Read operation: it queries and displays information without side effects. The tool does not create, modify, delete, or execute code—it only examines and reports differences between two plugin versions.
From the tool's definition The tool performs comparison operations between plugins ("Compare a local plugin with a WordPress.org plugin"), which is a data retrieval and analysis activity.
Attacks that exploit this kind of access
Compare a local plugin with a WordPress.org plugin. It is categorised as a Read tool in the WordPress Plugin Directory MCP Server MCP Server, which means it retrieves data without modifying state.
Register the WordPress Plugin Directory MCP Server MCP server in PolicyLayer and add a rule for compare_plugins: 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 WordPress Plugin Directory MCP Server. Nothing to install.
compare_plugins 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 compare_plugins 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 compare_plugins. 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.
compare_plugins is provided by the WordPress Plugin Directory MCP Server MCP server (juanma-wp/wordpress-org-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 →