Medium Risk

create_custom_application

create_custom_application

How to control create_custom_application ↓

What create_custom_application does on Fortimanager

AI agents use create_custom_application 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.

Medium Risk

Why create_custom_application needs a policy

Creating custom applications in FortiManager is a Write operation—it creates or modifies security policy data reversibly. However, severity is elevated to 'high' rather than 'medium' because misuse could allow an AI agent to define malicious applications or bypass application controls, affecting network security posture across managed devices.

From the tool's definition Tool name 'create_custom_application' indicates creation of a new application definition in FortiManager. The description is empty, but the name and context (FortiManager security policy management) strongly suggest this modifies security configurations.

Documented attack patterns abuse exactly the kind of access create_custom_application gives an agent:

How to control create_custom_application

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_custom_application:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_custom_application": {
      "limits": [
        {
          "counter": "create_custom_application_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

create_custom_application 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.

  1. Create a free account and register Fortimanager — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about create_custom_application

What does the create_custom_application tool do? +

create_custom_application. 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.

How do I enforce a policy on create_custom_application? +

Register the Fortimanager MCP server in PolicyLayer and add a rule for create_custom_application: 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.

What risk level is create_custom_application? +

create_custom_application is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_custom_application? +

Yes. Add a rate_limit block to the create_custom_application 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.

How do I block create_custom_application completely? +

Set action: deny in the PolicyLayer policy for create_custom_application. 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.

What MCP server provides create_custom_application? +

create_custom_application 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.

Enforce policy on every Fortimanager tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.