recommend_model
Routes a population or a plain-language intent to the model that fits it, then lists this workspace’s own models of that kind so an agent can act, and names how to create one when there is none. Read-only.
What it needs
| Argument | Type | Required | Description |
|---|---|---|---|
population | any | No | |
intent | any | No |
What it returns
The model family that fits what you want to score, the org's own models of that family so you can act on one, and how to create one when there is none.
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 recommend_model: routes a population or a plain-language intent to the model that fits it, then lists this workspace’s own models of that kind so an agent can act, and names how to create one when there is none.{ "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "recommend_model", "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.