reload_device_list
AI agents call reload_device_list to retrieve information from FortiManager MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The verb 'reload' combined with 'device_list' most naturally indicates retrieving or refreshing a list of devices from FortiManager—a read operation with no state changes. However, empty description reduces confidence. If this tool instead triggers a device reboot/restart operation (rare interpretation), severity would be Execute/critical.
From the tool's definition Tool name 'reload_device_list' indicates a refresh/query operation. Description is empty, so classification relies on naming pattern. Sibling tools include read operations (assign, add, clone operations typical in device management contexts).
Attacks that exploit this kind of access
reload_device_list. It is categorised as a Read tool in the FortiManager MCP Server MCP Server, which means it retrieves data without modifying state.
Register the FortiManager MCP Server MCP server in PolicyLayer and add a rule for reload_device_list: 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 MCP Server. Nothing to install.
reload_device_list is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the reload_device_list 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 reload_device_list. 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.
reload_device_list is provided by the FortiManager MCP Server MCP server (rstierli/fortimanager-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →