AI agents use authorize_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.
Based on the tool name 'authorize_device', this likely grants authorization or approval to a network device in FortiManager, which is a Write-level action (modifying access/trust state). However, with no description available, confidence is low. The severity is high because authorizing a device in a network management system could allow untrusted devices to gain network access.
From the tool's definition Tool name 'authorize_device'; description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access authorize_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 authorize_device:
{
"version": "1",
"default": "deny",
"tools": {
"authorize_device": {
"limits": [
{
"counter": "authorize_device_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}authorize_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.
authorize_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 authorize_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.
authorize_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 authorize_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 authorize_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.
authorize_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.