model_set_current · Flex Sensor Agent MCP: Risk & Policy

WHAT IT DOES

What model_set_current does on Flex Sensor Agent

AI agents use model_set_current to create or update resources in Flex Sensor Agent — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Flex Sensor Agent environment.

WHY IT NEEDS A POLICY

Why model_set_current needs a policy

This tool modifies application state by changing which model is active, but the change is reversible (another model can be set as current instead). It does not execute simulations, delete data, export results, or transfer money. The action is a configuration change internal to the COMSOL application context.

From the tool's definition Tool name 'model_set_current' and description 'Set the current active model for subsequent operations' indicate state modification that selects or activates a model for use.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

model_set_current Rate-limited

model_set_current 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": {
    "model_set_current": {
      "limits": [
        {
          "counter": "model_set_current_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 Flex Sensor Agent, so you can run agents against it safely.

FAQ

Questions about model_set_current

What does the model_set_current tool do? +

Set the current active model for subsequent operations. It is categorised as a Write tool in the Flex Sensor Agent MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on model_set_current? +

Register the Flex Sensor Agent MCP server in PolicyLayer and add a rule for model_set_current: 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 Flex Sensor Agent. Nothing to install.

What risk level is model_set_current? +

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

Can I rate-limit model_set_current? +

Yes. Add a rate_limit block to the model_set_current 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 model_set_current completely? +

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

model_set_current is provided by the Flex Sensor Agent MCP server (tonghui666/flex-sensor-agent-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.