Create an nginx config for a domain
AI agents use fleet_nginx_add to create or update resources in Fleet — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Fleet environment.
The tool creates Nginx configuration files for domains, which is a Write operation—it generates new configuration that affects production web server behavior. Severity is high because misconfigured Nginx can disrupt service availability, expose sensitive headers, or create security vulnerabilities (e.g., incorrect CORS, TLS settings, or routing), but the operation itself is not destructive (configs can be…
From the tool's definition Tool name 'fleet_nginx_add' and description 'Create an nginx config for a domain' indicate creation of configuration data. This is a reversible modification operation (configs can be updated or deleted).
Documented attack patterns abuse exactly the kind of access fleet_nginx_add gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Fleet, and nothing reaches the server without passing your rules. This is the rule we recommend for fleet_nginx_add:
{
"version": "1",
"default": "deny",
"tools": {
"fleet_nginx_add": {
"limits": [
{
"counter": "fleet_nginx_add_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} fleet_nginx_add 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.
Create an nginx config for a domain. It is categorised as a Write tool in the Fleet MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Fleet MCP server in PolicyLayer and add a rule for fleet_nginx_add: 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 Fleet. Nothing to install.
fleet_nginx_add 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 fleet_nginx_add 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 fleet_nginx_add. 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.
fleet_nginx_add is provided by the Fleet MCP server (wrxck/fleet). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Fleet, 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.
39 Fleet tools catalogued and risk-classified — across an index of 43,000+ MCP servers.