AI agents call delete_post to permanently remove resources in Velog — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes blog post data from Velog. Deletion cannot be undone, meeting the definition of Destructive category. The severity is high because an AI agent misusing this tool could permanently erase user content, though the blast radius is limited to individual posts rather than account-wide or system-wide destruction (which would be critical).
From the tool's definition Tool name is 'delete_post' and description states 'Delete a post on Velog'. Delete operations are irreversible and result in permanent data loss.
Documented attack patterns abuse exactly the kind of access delete_post gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Velog, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_post:
{
"version": "1",
"default": "deny",
"hide": [
"delete_post"
]
}delete_post disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete a post on Velog (requires authentication). It is categorised as a Destructive tool in the Velog MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Velog MCP server in PolicyLayer and add a rule for 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 Velog. Nothing to install.
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 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 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.
delete_post is provided by the Velog MCP server (stonehee99/velog-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Velog, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
10 Velog tools catalogued and risk-classified — across an index of 43,000+ MCP servers.