Add or replace a standalone /.well-known/ handler at a domain that does NOT otherwise proxy to the federated app. Use this on an apex domain to delegate Matrix federation via
AI agents use caddy_set_wellknown to create or update resources in Crow — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Crow environment.
This tool modifies web server configuration by adding or replacing a .well-known handler for a domain. This is a Write operation because it creates or updates configuration state reversibly—the handler can be removed or replaced later. It's not Execute (doesn't run arbitrary code), not Destructive (changes are reversible), and not Read (it modifies rather than retrieves).
From the tool's definition Tool description states 'Add or replace a standalone /.well-known/ handler' which are operations that create or modify configuration.
Documented attack patterns abuse exactly the kind of access caddy_set_wellknown gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crow, and nothing reaches the server without passing your rules. This is the rule we recommend for caddy_set_wellknown:
{
"version": "1",
"default": "deny",
"tools": {
"caddy_set_wellknown": {
"limits": [
{
"counter": "caddy_set_wellknown_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}caddy_set_wellknown 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.
Add or replace a standalone /.well-known/ handler at a domain that does NOT otherwise proxy to the federated app. Use this on an apex domain to delegate Matrix federation via. It is categorised as a Write tool in the Crow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Crow MCP server in PolicyLayer and add a rule for caddy_set_wellknown: 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_set_wellknown 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_set_wellknown 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_set_wellknown. 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_set_wellknown 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.
Start from Crow, 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.
576 Crow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.