create_threat_model · Devici MCP Server MCP: Risk & Policy

WHAT IT DOES

What create_threat_model does on Devici MCP Server

AI agents use create_threat_model to create or update resources in Devici MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Devici MCP Server environment.

WHY IT NEEDS A POLICY

Why create_threat_model needs a policy

This tool creates a new threat model resource reversibly. It is a Write operation because it modifies the system state by adding new data. Severity is medium because threat models may influence security decisions, but the operation itself is not destructive, financial, or code-execution.

From the tool's definition Tool description states 'Create a new threat model', which is an explicit create operation that generates new data in the Devici system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_threat_model Rate-limited

create_threat_model 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_threat_model": {
      "limits": [
        {
          "counter": "create_threat_model_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Devici MCP Server, so you can run agents against it safely.

FAQ

Questions about create_threat_model

What does the create_threat_model tool do? +

Create a new threat model. It is categorised as a Write tool in the Devici MCP Server 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_threat_model? +

Register the Devici MCP Server MCP server in PolicyLayer and add a rule for create_threat_model: 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 Devici MCP Server. Nothing to install.

What risk level is create_threat_model? +

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

Can I rate-limit create_threat_model? +

Yes. Add a rate_limit block to the create_threat_model 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_threat_model completely? +

Set action: deny in the PolicyLayer policy for create_threat_model. 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_threat_model? +

create_threat_model is provided by the Devici MCP Server MCP server (sdelements/devici-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.