get_readout
The model-quality readout as structured text: AUC named and explained, lift in the top band, what it trained on, the features that drove the score, and the Feature Stability Score. Metrics the model does not have are reported as unavailable rather than guessed.
What it needs
| Argument | Type | Required | Description |
|---|---|---|---|
model_id | string | Yes |
What it returns
The model-quality readout in sections: what counts as the outcome in plain words, AUC and the lift in the top band with what each means, what the model trained on, the factors that drove the score, and the Feature Stability Score.
Credential
An app session token, from an authenticated app.ax1om.ai session. Call it with only an API key and you get a plain refusal saying so, rather than a confusing 401.
Network call: yes. The full credential split is on authentication.
Example call
Most readers never write the protocol themselves: the agent does, once the server is connected. Both forms are the same call.
Use the ax1om MCP server.Call get_readout: the model-quality readout as structured text: AUC named and explained, lift in the top band, what it trained on, the features that drove the score, and the Feature Stability Score.{ "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "get_readout", "arguments": {} }}The arguments object is whatever this tool's own input schema declares. An MCP client reads that schema from the server, so it is the server that answers for the exact shape rather than this page.
Notes
- The readout is structured text. There is no PDF export of it.