Read Caddy config at any JSON path. Returns the full config when path is empty, or a subtree at a specific path (e.g.,
AI agents call caddy_config_get to retrieve information from Caddy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
caddy_config_get performs a read-only query of Caddy's configuration state. It retrieves data via JSON path without creating, modifying, or deleting anything. This fits the Read category.
From the tool's definition Tool name and description indicate it "Read[s] Caddy config" and "Returns the full config when path is empty, or a subtree at a specific path".
Documented attack patterns abuse exactly the kind of access caddy_config_get 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_get:
{
"version": "1",
"default": "deny",
"tools": {
"caddy_config_get": {}
}
} caddy_config_get is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Read Caddy config at any JSON path. Returns the full config when path is empty, or a subtree at a specific path (e.g.,. It is categorised as a Read tool in the Caddy MCP Server, which means it retrieves data without modifying state.
Register the Caddy MCP server in PolicyLayer and add a rule for caddy_config_get: 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_get is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the caddy_config_get 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_get. 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_get 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.