transkribus_recog_text2image

What transkribus_recog_text2image does on Transkribus

AI agents invoke transkribus_recog_text2image to trigger actions in Transkribus. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

Why transkribus_recog_text2image is rated High

This tool executes a machine learning operation (Text2Image alignment) on behalf of the user. It is not a simple read (it produces computed outputs with side effects in the collection), not a write in the reversible sense (alignment results are stored), and not destructive by itself. However, it runs an external computational process whose outcomes depend on provided arguments, fitting the Execute category.

From the tool's definition Tool name contains 'run' action ('Run Text2Image alignment') and triggers an external operation (alignment/recognition model execution) whose effects depend on arguments (model selection, collection context).

The rule that runs transkribus_recog_text2image 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_recog_text2image, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "transkribus_recog_text2image": {
      "limits": [
        {
          "counter": "transkribus_recog_text2image_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

Questions about transkribus_recog_text2image