upload_csv

MCP server · Train and read

Uploads a scrubbed CSV as a training dataset and returns the column metadata ax1om read from it. Max 100MB, .csv only.

What it needs

Argument	Type	Required	Description
file_path	any	No
content	any	No
name	any	No
description	any	No
object_role	any	No
data_origin	any	No

What it returns

The column metadata ax1om read from the uploaded file, the id of the CSV workspace connection the upload feeds, and the next steps to create a model on it.

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.

Ask your agent

prompt

Use the ax1om MCP server.
Call upload_csv: uploads a scrubbed CSV as a training dataset and returns the column metadata ax1om read from it.

JSON-RPC

POST https://api.ax1om.ai/mcp

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "upload_csv",
    "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

• No export ready yet? Every ax1om account ships with a sample CRM dataset, and a model trained on it reads back through the same tools.