Hugging Face Dataset Details

huggingfacehub/get-dataset

Returns the Hugging Face Hub record of one dataset repo given its owner and name: downloads over the last 30 days, likes, dates, head commit, storage used, up to 40 tags, a card summary (`description`, clipped to 500 characters), the card header (`cardData`: licence, languages, task categories, size category and so on), and the file count with the first 30 file names. Strings, lists and objects are bounded. Also serves the Open Australian Legal Corpus (owner isaacus, name open-australian-legal-corpus). Each repo has its own licence, set by its authors; it appears in `cardData.license` and in the `license:` tag where they set it. Hugging Face Hub metadata, served by Eden Engine; not an official Hugging Face product.

activeper callv1

Price

$0.0026 per call

You pay the price shown. If a call turns out to cost more than its quote, you pay the actual price, capped at twice the quote. No monthly minimum. Top-ups start at $0.50.

Data source

Hugging Face

Data from the Hugging Face Hub (https://huggingface.co). Each model and dataset carries its own licence, set by its authors on the repo card. Served by Eden Engine; not an official Hugging Face product.

Use it

Five steps: search, inspect, learn, run, settle. No per-tool setup; your agent reaches this tool through the meta-tools it already has.

Connect once and your AI can find and run this tool, and any other it needs.

Install it Create an account

agent

// 1. search: find the tool
omnial_search({ query: "what you need" })

// 2. inspect: price and input schema
omnial_inspect({ tool: "huggingfacehub/get-dataset" })

// 3. learn: read the usage guide at runtime
omnial_learn({ tool: "huggingfacehub/get-dataset" })

// 4. run: price the exact call first, then run it
omnial_execute({ tool: "huggingfacehub/get-dataset", input: { /* see input_schema */ }, dry_run: true })
omnial_execute({ tool: "huggingfacehub/get-dataset", input: { /* ... */ } })

// 5. settle: the call is charged when it finishes, nothing to do

Not connected yet? Point your MCP client at https://mcp.eden-engine.com/mcp, then copy a config for your client.

Pricing

Every charge this tool can incur.

Charge	Price
Per call	$0.0026

Updated: Oct 25, 2026

Input and output schemas

Input schema

input_schema.json

{
  "type": "object",
  "required": [
    "owner",
    "name"
  ],
  "properties": {
    "name": {
      "type": "string",
      "pattern": "^[A-Za-z0-9][A-Za-z0-9._-]*$",
      "maxLength": 96,
      "minLength": 1,
      "description": "Repo name part of the repo id, for example bert-base-uncased."
    },
    "owner": {
      "type": "string",
      "pattern": "^[A-Za-z0-9][A-Za-z0-9._-]*$",
      "maxLength": 96,
      "minLength": 1,
      "description": "Owner (user or organisation) part of the repo id, for example google-bert in google-bert/bert-base-uncased."
    }
  },
  "additionalProperties": false
}

Output schema

output_schema.json

{
  "type": "object",
  "required": [
    "id",
    "fileCount"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Repo id, owner/name."
    },
    "sha": {
      "type": "string",
      "description": "Head commit of the repo."
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "At most 40 tags (library, task, language, licence:..., dataset:... and so on)."
    },
    "files": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "The first 30 file names."
    },
    "gated": {
      "type": [
        "boolean",
        "string"
      ],
      "description": "false for an open repo, or \"auto\" / \"manual\" when access needs a request."
    },
    "likes": {
      "type": "integer"
    },
    "author": {
      "type": "string"
    },
    "spaces": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "The first 10 Space ids."
    },
    "clipped": {
      "type": "boolean",
      "description": "True when the hook shortened a string, list or object; strings end with a note giving the count dropped."
    },
    "private": {
      "type": "boolean"
    },
    "cardData": {
      "type": "object",
      "description": "The repo card's YAML header (licence, language, base model, datasets, size category and so on), clipped.",
      "additionalProperties": true
    },
    "disabled": {
      "type": "boolean"
    },
    "createdAt": {
      "type": "string"
    },
    "downloads": {
      "type": "integer",
      "description": "Downloads in the last 30 days."
    },
    "fileCount": {
      "type": "integer",
      "description": "Files in the repo."
    },
    "spaceCount": {
      "type": "integer",
      "description": "Spaces that use this repo; models only."
    },
    "description": {
      "type": [
        "string",
        "null"
      ],
      "description": "Dataset card summary, clipped to 500 characters; datasets only."
    },
    "safetensors": {
      "type": "object",
      "description": "Parameter counts by dtype and the total; models with safetensors weights only.",
      "additionalProperties": true
    },
    "usedStorage": {
      "type": "integer",
      "description": "Bytes the repo uses."
    },
    "lastModified": {
      "type": "string"
    },
    "library_name": {
      "type": [
        "string",
        "null"
      ]
    },
    "pipeline_tag": {
      "type": [
        "string",
        "null"
      ],
      "description": "Task, for example text-classification; absent or null when the authors set none."
    },
    "trendingScore": {
      "type": "number"
    }
  },
  "description": "One dataset record, reduced by the hook (see `clipped`).",
  "additionalProperties": true
}