search_datasets

Active

declared in 0.1.0

Search Hugging Face Hub datasets with filters for author, language, and task_categories; sort by downloads, likes, or lastModified; returns dataset id, downloads, likes, and tags.

Parameters schema

{
  "type": "object",
  "examples": [
    {
      "limit": 20,
      "search": "imagenet"
    },
    {
      "sort": "likes",
      "limit": 15,
      "author": "wikipedia",
      "language": "en",
      "task_categories": "text-classification"
    }
  ],
  "properties": {
    "full": {
      "type": "boolean"
    },
    "sort": {
      "type": "string"
    },
    "limit": {
      "type": "number"
    },
    "author": {
      "type": "string"
    },
    "search": {
      "type": "string"
    },
    "language": {
      "type": "string"
    },
    "direction": {
      "type": "string"
    },
    "task_categories": {
      "type": "string",
      "description": "Comma-separated task categories"
    }
  }
}

What this tool wraps· 0 endpoints

min confidence0.70 0.50

No endpoints wrapped at confidence ≥ 0.70.

Parent server

Huggingface

https://github.com/pipeworx-io/mcp-huggingface

1/7 registries

View full server →