Upload Dataset
The upload_dataset tool creates a new dataset on the Knowledgator platform by uploading validated in-memory records or raw JSON string content.
Tool Overview
- Tool Name:
upload_dataset - Underlying Endpoint:
POST /datasets/ - SDK Methods:
kg.datasets.create(..., file=...)/kg.datasets.upload(Python) /kg.datasets.upload(TypeScript) - Architecture: Stateless In-Memory Proxy — The MCP server does not store uploaded files on its local container filesystem. It streams data directly to the API via multipart form data without persistent disk storage.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
name | String | Yes | Dataset name (e.g. "Customer Feedback Sentiment"). Must match the pattern ^[a-zA-Z0-9- .()]+$. |
data | Array of Objects | No | In-memory list of sample dictionaries. Either data or json_content must be provided. |
json_content | String | No | Raw JSON string representing the dataset samples array. |
dataset_type | String | No | Target task type: classification (comprehend-it), ner (extract-it), instruct-it, or relation-extraction. Defaults to classification. |
short_description | String | No | Optional human-readable description (max 1024 characters). |
Behavior & Safeguards
- Schema Validation: The tool automatically verifies that the payload is a non-empty array of objects containing required text and label keys for the given task type before transmitting to the platform.
- Stateless Memory Safety: Data is serialized to bytes directly in memory and streamed via multipart upload. No temporary files are leaked or retained inside the MCP container.
Example Usage
Natural Language Prompt to Agent
"Upload a 2-sample sentiment dataset named 'Feedback Sentiment' to Knowledgator."
Tool Call Arguments
{
"name": "upload_dataset",
"arguments": {
"name": "Feedback Sentiment",
"dataset_type": "classification",
"data": [
{
"text": "The delivery was remarkably quick and the product quality exceeded expectations.",
"label": "positive"
},
{
"text": "Item arrived damaged and customer support did not respond.",
"label": "negative"
}
],
"short_description": "Curated customer feedback samples"
}
}
Tool Response
{
"status": "success",
"dataset_id": "7ca64731-01be-4835-b6d8-6014e7a8e2cb",
"dataset_name": "Feedback Sentiment",
"sample_count": 2,
"dataset_type": "comprehend-it",
"format": "json",
"size_bytes": 284,
"dataset_status": "valid",
"short_description": "Curated customer feedback samples"
}