This record as markdown: /tools/kh0pper-crow/caddy-reload.md
What caddy_reload does on Crow
AI agents invoke caddy_reload to trigger actions in Crow. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why caddy_reload is rated High
Reloading a web server configuration is an operational action with real side effects: it can disrupt live traffic, change routing/TLS behavior, or cause outages if the config is invalid or malicious. It goes beyond a simple write as it actively applies and enforces a new configuration on a running system.
From the tool's definition 'Validate and apply the current Caddyfile via Caddy' — this triggers an external operation that reloads the Caddy web server configuration
Attacks that exploit this kind of access
The rule that runs caddy_reload safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Crow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For caddy_reload, this is the rule to start with:
caddy_reload stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Crow, apply this rule, and every caddy_reload call is checked against it from then on.
Questions about caddy_reload
Validate and apply the current Caddyfile via Caddy. It is categorised as a Execute tool in the Crow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Crow MCP server in PolicyLayer and add a rule for caddy_reload: 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 Crow. Nothing to install.
caddy_reload is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the caddy_reload 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_reload. 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_reload is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Crow, and thousands of servers like it.
This server
Across the catalogue