set_target_model · SensorMCP Server MCP: Risk & Policy

WHAT IT DOES

What set_target_model does on SensorMCP Server

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

WHY IT NEEDS A POLICY

Why set_target_model needs a policy

The tool appears to set or update a target model parameter, which constitutes reversible data modification. Without explicit documentation, confidence is moderate. Classified as Write rather than Execute because it appears to be configuration-setting rather than triggering model training or external operations. Not Destructive since model configuration changes are typically reversible.

From the tool's definition Tool name 'set_target_model' with empty description. Based on sibling tools 'set_base_model' and 'train_model' context, this likely modifies model configuration state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

set_target_model Rate-limited

set_target_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": {
    "set_target_model": {
      "limits": [
        {
          "counter": "set_target_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 SensorMCP Server, so you can run agents against it safely.

FAQ

Questions about set_target_model

What does the set_target_model tool do? +

set_target_model. It is categorised as a Write tool in the SensorMCP 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 set_target_model? +

Register the SensorMCP Server MCP server in PolicyLayer and add a rule for set_target_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 SensorMCP Server. Nothing to install.

What risk level is set_target_model? +

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

Can I rate-limit set_target_model? +

Yes. Add a rate_limit block to the set_target_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 set_target_model completely? +

Set action: deny in the PolicyLayer policy for set_target_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 set_target_model? +

set_target_model is provided by the SensorMCP Server MCP server (sensormcp/sensor-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.