score_records
Live scoring through POST /v1/score. Returns a 0-100 score per record plus the conversion likelihood it ranks by, and the factors behind it when explain is on. Max 1000 records per request. Metered.
Once a model is trained this is the tool an agent calls in normal operation. Set explain to true and each score comes back with the factors behind it, which is what lets the agent explain its own prioritization to a human instead of asserting it.
What it needs
| Argument | Type | Required | Description |
|---|---|---|---|
model_id | string | Yes | |
records | array | Yes | |
explain | boolean | No |
What it returns
A 0-100 score for every record sent, in the order sent, each with the conversion likelihood it ranks by and the top reasons behind it when explain is on, plus how many records were scored, the model's validation state, and what the call used against your monthly allowance.
Credential
An API key (ax1m_sk_..., minted in the app under Settings, API keys). API keys authorize live scoring only.
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 score_records: live scoring through POST /v1/score.{ "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "score_records", "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
- Read the number correctly. The score is a 0-100 ranking of conversion likelihood. It is not a percentage chance of conversion, and the per-record factors do not sum to it.
- Say "ranks near the top on conversion likelihood", never "87% likely to convert".