transkribus_model_get_train_data_docs

What transkribus_model_get_train_data_docs does on Transkribus

AI agents call transkribus_model_get_train_data_docs 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_train_data_docs is rated Low

This tool retrieves metadata or references about which documents were used to train a model. It queries existing data without modifying, deleting, or executing operations. The blast radius of misuse is minimal—an attacker could learn what training data was used, but cannot alter it or trigger external operations. This is a straightforward Read operation.

From the tool's definition Tool name and description indicate retrieval of documents: 'Get the documents used as training data for a model.' The verb 'Get' and lack of modification language (create, update, delete) confirm read-only behavior.

The rule that runs transkribus_model_get_train_data_docs 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_train_data_docs, this is the rule to start with:

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

Questions about transkribus_model_get_train_data_docs