Delete a WordPress media item.
AI agents call wordpress_delete_media to permanently remove resources in MCP Wordpress — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs an irreversible deletion operation on WordPress media assets. Once deleted, media items cannot be recovered through normal means, making this a destructive action with potentially significant blast radius if triggered inappropriately by an AI agent (e.g., deleting important site images, logos, or attachments).
From the tool's definition Tool name contains 'delete' and description states 'Delete a WordPress media item.' This irreversibly removes media from WordPress.
Attacks that exploit this kind of access
Delete a WordPress media item. It is categorised as a Destructive tool in the MCP Wordpress MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Wordpress MCP server in PolicyLayer and add a rule for wordpress_delete_media: 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 MCP Wordpress. Nothing to install.
wordpress_delete_media is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the wordpress_delete_media 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 wordpress_delete_media. 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.
wordpress_delete_media is provided by the MCP Wordpress MCP server (crunchtools/mcp-wordpress). 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 →