anthropic_list_models

What anthropic_list_models does on UnClick

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

Parameters from the server's own tool schema.

Why anthropic_list_models is rated Low

This tool queries and returns metadata about available Claude models from the Anthropic API. It performs a read-only operation with no side effects, matching the 'Read' category profile. The severity is low because listing model information poses minimal risk; misuse cannot cause data loss, financial harm, or unintended execution of code. Confidence is high (0.95) because the intent and behavior are unambiguous.

From the tool's definition Tool name indicates 'list' operation; description states 'List all Claude models available via the Anthropic API' — a pure retrieval action with no modification, deletion, or execution of external operations.

Risk signalsHandles credentials or secrets (api_key)

The rule that runs anthropic_list_models safely

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

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

Questions about anthropic_list_models