AI agents call test_fortiguard_connection as a supporting operation in Fortimanager workflows.
The name suggests a connectivity test to FortiGuard, which would typically be a read/execute operation with low impact. However, with no description available, confidence is very low. Based on name alone, testing a connection is a low-severity read-like or execute-like action with minimal blast radius.
From the tool's definition Tool name is 'test_fortiguard_connection'; description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access test_fortiguard_connection 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 test_fortiguard_connection:
{
"version": "1",
"default": "deny",
"tools": {
"test_fortiguard_connection": {
"limits": [
{
"counter": "test_fortiguard_connection_rate",
"window": "minute",
"max": 60,
"scope": "grant"
}
]
}
}
}test_fortiguard_connection gets a rate cap, and everything else on the server is denied unless you say otherwise.
Free to start. No card required.
test_fortiguard_connection. It is categorised as a Other tool in the Fortimanager MCP Server, which means it performs auxiliary operations.
Register the Fortimanager MCP server in PolicyLayer and add a rule for test_fortiguard_connection: 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.
test_fortiguard_connection is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the test_fortiguard_connection 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 test_fortiguard_connection. 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.
test_fortiguard_connection 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.