model_save · Flex Sensor Agent MCP: Risk & Policy

WHAT IT DOES

What model_save does on Flex Sensor Agent

AI agents use model_save 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_save needs a policy

This tool creates or modifies stored simulation models reversibly—a classic Write operation. It is not Destructive because saving does not irreversibly delete data (overwriting is reversible via version control or re-export). It is not Execute because it does not run arbitrary code or trigger external processes with user-supplied arguments.

From the tool's definition Tool name 'model_save' indicates a save/persist operation. Within the COMSOL Multiphysics simulation context (flex_sensor_*), saving a model likely modifies persistent state by writing simulation model files to disk.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

model_save Rate-limited

model_save 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_save": {
      "limits": [
        {
          "counter": "model_save_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_save

What does the model_save tool do? +

model_save. 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_save? +

Register the Flex Sensor Agent MCP server in PolicyLayer and add a rule for model_save: 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_save? +

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

Can I rate-limit model_save? +

Yes. Add a rate_limit block to the model_save 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_save completely? +

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

model_save 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.