Skip to content

create_scoring_model

MCP server · Train and read

Creates the conversion model: which leads or contacts convert, learned from your own conversion history. Bind the outcome to a CRM template or, for an uploaded CSV, to your own columns. Field selection is optional, and label, identifier and personal-data columns are never selectable: naming one is refused rather than silently dropped. Returns the model id to train.

What it needs

ArgumentTypeRequiredDescription
namestringYes
connection_idstringYes
templatestringNo
success_fieldanyNo
success_operatorstringNo
success_valueanyNo
success_date_fieldanyNo
fieldsanyNo
exclude_fieldsanyNo
created_date_fieldanyNo
include_engagementanyNo
descriptionanyNo

What it returns

The new model's id and the score it belongs to, confirmation that it is assigned to that score's rule without being activated, the validated contract it was built from, and the columns, date binding and activity sources it will train on.

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.

prompt
Use the ax1om MCP server.
Call create_scoring_model: creates the conversion model: which leads or contacts convert, learned from your own conversion history.

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.

Need help?Contact supportLatest changes?See the changelog
Something wrong?Check system statusComing soon