models_status

What models_status does on Yaver

AI agents call models_status to retrieve information from Yaver without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why models_status is rated Low

This tool only retrieves and reports the current status of Ollama (a local LLM framework), similar to status checks or health probes. It has no side effects, does not modify data, execute code, or trigger operations. The information returned is read-only diagnostic data. Severity is low because misuse would only expose system state information without enabling harmful actions.

From the tool's definition Tool name 'models_status' and description 'Check Ollama status: running, port, GPU, model count' indicates a read-only query operation that retrieves state information without modification or execution of external commands.

The rule that runs models_status safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For models_status, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "models_status": {}
  }
}

Questions about models_status