transkribus_model_get_validation_data

What transkribus_model_get_validation_data does on Transkribus

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

Why transkribus_model_get_validation_data is rated Low

This tool retrieves validation data associated with a model. The verb 'get' and the absence of any language indicating modification, deletion, or execution of operations clearly indicate a Read action. The data returned is informational and does not alter any state. Blast radius is minimal: exposure would allow an attacker to view model validation metrics, which is a low-severity information disclosure.

From the tool's definition The tool name contains 'get' and the description states 'Get the validation data for a model' — a pure retrieval operation with no modification or side effects.

The rule that runs transkribus_model_get_validation_data safely

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

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

Questions about transkribus_model_get_validation_data