Manage config snapshots for rollback. Snapshots are auto-captured before caddy_load and kept in-memory (last 10). Actions:
AI agents use caddy_revert to create or update resources in Caddy — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Caddy environment.
This tool manages snapshots and enables rollback of Caddy configuration. Reverting to a prior configuration is a reversible write operation (it restores a previous state rather than permanently deleting anything), making Write the appropriate category. However, reverting a live web server config could cause service disruption or expose security misconfigurations, warranting high severity.
From the tool's definition Manage config snapshots for rollback. Snapshots are auto-captured before caddy_load and kept in-memory (last 10).
Documented attack patterns abuse exactly the kind of access caddy_revert 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_revert:
{
"version": "1",
"default": "deny",
"tools": {
"caddy_revert": {
"limits": [
{
"counter": "caddy_revert_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} caddy_revert stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Manage config snapshots for rollback. Snapshots are auto-captured before caddy_load and kept in-memory (last 10). Actions:. It is categorised as a Write tool in the Caddy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Caddy MCP server in PolicyLayer and add a rule for caddy_revert: 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_revert is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the caddy_revert 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_revert. 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_revert 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.