caddy_load

THE RISK

Critical Risk

Why caddy_load needs a policy

Atomically replacing the entire Caddy configuration is a highly destructive operation — it overwrites all existing routes, TLS settings, reverse proxies, and server definitions in one shot. While Caddy may support rollback in some scenarios, the operation itself unconditionally overwrites the full running config with no partial or reversible merge.

From the tool's definition Replace the entire Caddy configuration atomically

Risk signalsBulk/mass operation — affects multiple targets

Documented attack patterns abuse exactly the kind of access caddy_load gives an agent:

POLICY

How to control caddy_load

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_load:

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "caddy_load"
  ]
}

caddy_load disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

Create a free account and register Caddy — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Caddy tools

Destructive caddy_config_delete Delete config at a JSON path. Removes the config node at the specified path. Deleting a pa Destructive caddy_remove_route Remove a route. Target by @id (preferred — stable across reorderings) or by array index on Execute caddy_stop Gracefully shut down the Caddy server. Requires confirm=true to prevent accidental shutdow Write caddy_add_route Add a route with full control over match conditions and handlers. Supports any Caddy handl Write caddy_config_set Write config at a JSON path. Mode Write caddy_reverse_proxy Add a reverse proxy route. The most common operation — just specify where traffic comes fr Write caddy_revert Manage config snapshots for rollback. Snapshots are auto-captured before caddy_load and ke Write caddy_tls Get or configure TLS/HTTPS settings. Actions:

All 18 Caddy tools →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Critical-risk tools in Caddy → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about caddy_load

What does the caddy_load tool do? +

Replace the entire Caddy configuration atomically. Accepts a JSON config object, or a Caddyfile string with format=. 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.

How do I enforce a policy on caddy_load? +

Register the Caddy MCP server in PolicyLayer and add a rule for caddy_load: 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.

What risk level is caddy_load? +

caddy_load is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit caddy_load? +

Yes. Add a rate_limit block to the caddy_load 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.

How do I block caddy_load completely? +

Set action: deny in the PolicyLayer policy for caddy_load. 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.

What MCP server provides caddy_load? +

caddy_load 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.

Enforce policy on every Caddy tool call.

Start from Caddy, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →