Delete config at a JSON path. Removes the config node at the specified path. Deleting a parent node also deletes every descendant -- e.g. deleting
AI agents call caddy_config_delete to permanently remove resources in Caddy — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes Caddy configuration nodes, which cannot be undone. Deleting parent nodes cascades to delete all descendants, potentially disabling critical web server routing, TLS, or reverse proxy configurations. The impact is irreversible (meeting the Destructive definition) and poses significant risk if an AI agent targets wrong paths.
From the tool's definition Tool name 'caddy_config_delete' and description explicitly states 'Delete config at a JSON path' and 'Removes the config node at the specified path. Deleting a parent node also deletes every descendant' — indicating irreversible deletion of configuration data.
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access caddy_config_delete gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Caddy, and nothing reaches the server without passing your rules. This is the rule we recommend for caddy_config_delete:
{
"version": "1",
"default": "deny",
"hide": [
"caddy_config_delete"
]
} caddy_config_delete 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 config at a JSON path. Removes the config node at the specified path. Deleting a parent node also deletes every descendant -- e.g. deleting. It is categorised as a Destructive tool in the Caddy MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Caddy MCP server in PolicyLayer and add a rule for caddy_config_delete: 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 Caddy. Nothing to install.
caddy_config_delete 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 caddy_config_delete 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 caddy_config_delete. 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.
caddy_config_delete is provided by the Caddy MCP server (yawlabs/caddy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Caddy, 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.
18 Caddy tools catalogued and risk-classified — across an index of 43,000+ MCP servers.