Delete a post by ID.
AI agents call ghost_delete_post to permanently remove resources in Ghost CMS MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs an irreversible deletion operation on a post resource. Deletion cannot be undone without restore operations, making this Destructive rather than Write. High severity reflects that an AI agent misusing this tool could permanently remove published content, affecting editorial workflows and user-facing content. The confidence is very high due to explicit 'delete' language in both name and description.
From the tool's definition Tool name 'ghost_delete_post' and description 'Delete a post by ID' directly indicate irreversible deletion of data.
Attacks that exploit this kind of access
Delete a post by ID. It is categorised as a Destructive tool in the Ghost CMS MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ghost CMS MCP server in PolicyLayer and add a rule for ghost_delete_post: 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 Ghost CMS MCP. Nothing to install.
ghost_delete_post 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 ghost_delete_post 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 ghost_delete_post. 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.
ghost_delete_post is provided by the Ghost CMS MCP server (matveev-pavel/ghost-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 →