AI agents use create_model_device to create or update resources in Fortimanager — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Fortimanager environment.
Creating a device in FortiManager is a reversible write operation that adds a new configuration object. While it modifies system state, it is not destructive (can be deleted) and does not execute arbitrary code or cause financial impact. Confidence is slightly reduced due to empty description, but the name and sibling tool context provide strong categorical signals.
From the tool's definition Tool name is 'create_model_device' which indicates creation of a device model/entry. The sibling tools on this server (add_device_to_group, add_real_device, add_template_to_group, etc.) all perform write operations that create or modify FortiManager…
Documented attack patterns abuse exactly the kind of access create_model_device gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Fortimanager, and nothing reaches the server without passing your rules. This is the rule we recommend for create_model_device:
{
"version": "1",
"default": "deny",
"tools": {
"create_model_device": {
"limits": [
{
"counter": "create_model_device_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_model_device 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_model_device. It is categorised as a Write tool in the Fortimanager MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Fortimanager MCP server in PolicyLayer and add a rule for create_model_device: 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 Fortimanager. Nothing to install.
create_model_device 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 create_model_device 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 create_model_device. 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.
create_model_device is provided by the Fortimanager MCP server (jmpijll/fortimanager-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Fortimanager, 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.
584 Fortimanager tools catalogued and risk-classified — across an index of 43,000+ MCP servers.