# Hugging face dataset search

Search datasets on the Hugging Face Hub by name, author or tag: dataset id, description excerpt, tags (task, modality, language, size, licence), downloads. Takes search, author, filter and more, all optional.

Search datasets on the Hugging Face Hub by name, author or tag: dataset id, description excerpt, tags (task, modality, language, size, licence), downloads, likes, gated status and last update. Use it to find training or evaluation data for a domain.

- Tool ID: `huggingface/datasets-search`
- Name in the catalog: Hugging Face dataset search
- Provider: [Hugging Face](/providers/huggingface.md)
- Capability: [GitHub, npm & PyPI](/tools/developer-data/code.md)
- Price: no charge per call
- Authentication: an authorised Agentik workspace is required for execution, including zero-price tools.

## Pricing contract

No charge per call. A workspace is still needed so your agent can call it.


```json
{
  "model": "per_call",
  "amountUsd": 0
}
```

## Complete input schema


```json
{
  "type": "object",
  "properties": {
    "search": {
      "type": "string",
      "minLength": 1,
      "maxLength": 100,
      "description": "Words in the dataset id, e.g. 'finance'"
    },
    "author": {
      "type": "string",
      "pattern": "^[A-Za-z0-9][A-Za-z0-9._-]{0,95}$",
      "description": "User or organisation, e.g. 'HuggingFaceFW'"
    },
    "filter": {
      "type": "string",
      "pattern": "^[A-Za-z0-9:._/-]{2,80}$",
      "description": "Any Hub tag, e.g. 'language:fr', 'task_categories:text-classification' or 'license:mit'"
    },
    "sort": {
      "type": "string",
      "enum": [
        "downloads",
        "likes",
        "trendingScore",
        "lastModified",
        "createdAt"
      ],
      "default": "downloads",
      "description": "Sort key, always descending, e.g. 'likes'"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 30,
      "default": 10,
      "description": "Datasets to return, e.g. 10"
    }
  },
  "additionalProperties": false
}
```

## Published example

This is the provider tool’s published example. Replace example values with the user’s requested inputs, respecting the schema; do not execute an example merely to test a connection.


```json
{
  "tool_id": "huggingface/datasets-search",
  "input": {
    "search": "finance",
    "limit": 5
  }
}
```

## Execute and retrieve

Inspect again before execution, explain the price and obtain the required authority. Use MCP run_tool or POST /v1/run with this tool ID, valid input and an idempotency key. Save the returned run ID and follow the actual state. If Agentik answers that the tool is temporarily unavailable, do not retry it blindly; use discovery to propose an alternative.

A partial or uncertain result can still have consumed provider resources. Consult [billing](/docs/billing.md), [idempotency](/docs/idempotency.md) and [asynchronous results](/docs/async.md).

Licence: Hugging Face Hub metadata; each repository carries its own licence.

[Provider documentation](https://huggingface.co/docs/hub/api)

[REST inspection](https://api.agentik.cc/v1/tools/huggingface/datasets-search) · [OpenAPI](/openapi.json) · [Connection guide](/connect.md)

---

[HTML page](/providers/huggingface/datasets-search) · [Agent index](/llms.txt)