📌Overview

Purpose: To provide a robust MCP server for browsing and analyzing datasets hosted on the Hugging Face Hub via the Dataset Viewer API.

Overview: The Dataset Viewer MCP Server encompasses a suite of tools that facilitate interaction with various datasets. It enables users to validate, explore, and manipulate data effectively, granting both public and private dataset access through secure authentication.

Key Features:

• Enhanced Dataset Access: Utilizes the dataset:// URI scheme, offering comprehensive support for dataset configurations and splits, ensuring efficient data retrieval.

• Robust Tools Suite: Offers multiple tools including validation, information retrieval, pagination for dataset contents, statistical analysis, and search functionalities that enhance user experience and data exploration capabilities.

• Flexible Filtering and Download Options: Allows SQL-like filtering of dataset rows and supports full dataset downloads in Parquet format, meeting diverse user needs for data manipulation and analysis.

---

Dataset Viewer MCP Server

An MCP server for interacting with the Hugging Face Dataset Viewer API, providing capabilities to browse and analyze datasets hosted on the Hugging Face Hub.

Features

Resources

• Uses dataset:// URI scheme for accessing Hugging Face datasets
• Supports dataset configurations and splits
• Provides paginated access to dataset contents
• Handles authentication for private datasets
• Supports searching and filtering dataset contents
• Provides dataset statistics and analysis

Tools

The server provides the following tools:

1. validate

   • Check if a dataset exists and is accessible
   • Parameters:
     • dataset: Dataset identifier (e.g. 'stanfordnlp/imdb')
     • auth_token (optional): For private datasets

2. get_info

   • Get detailed information about a dataset
   • Parameters:
     • dataset: Dataset identifier
     • auth_token (optional): For private datasets

3. get_rows

   • Get paginated contents of a dataset
   • Parameters:
     • dataset: Dataset identifier
     • config: Configuration name
     • split: Split name
     • page (optional): Page number (0-based)
     • auth_token (optional): For private datasets

4. get_first_rows

   • Get first rows from a dataset split
   • Parameters:
     • dataset: Dataset identifier
     • config: Configuration name
     • split: Split name
     • auth_token (optional): For private datasets

5. get_statistics

   • Get statistics about a dataset split
   • Parameters:
     • dataset: Dataset identifier
     • config: Configuration name
     • split: Split name
     • auth_token (optional): For private datasets

6. search_dataset

   • Search for text within a dataset
   • Parameters:
     • dataset: Dataset identifier
     • config: Configuration name
     • split: Split name
     • query: Text to search for
     • auth_token (optional): For private datasets

7. filter

   • Filter rows using SQL-like conditions
   • Parameters:
     • dataset: Dataset identifier
     • config: Configuration name
     • split: Split name
     • where: SQL WHERE clause (e.g. "score > 0.5")
     • orderby (optional): SQL ORDER BY clause
     • page (optional): Page number (0-based)
     • auth_token (optional): For private datasets

8. get_parquet

   • Download entire dataset in Parquet format
   • Parameters:
     • dataset: Dataset identifier
     • auth_token (optional): For private datasets

Installation

Prerequisites

• Python 3.12 or higher
• uv - Fast Python package installer and resolver

Setup

1. Clone the repository:

git clone https://github.com/privetin/dataset-viewer.git
cd dataset-viewer

2. Create a virtual environment and install:

# Create virtual environment
uv venv

# Activate virtual environment
# On Unix:
source .venv/bin/activate
# On Windows:
.venv\Scripts\activate

# Install in development mode
uv add -e .

Configuration

Environment Variables

• HUGGINGFACE_TOKEN: Your Hugging Face API token for accessing private datasets

Claude Desktop Integration

Add the following to your Claude Desktop config file:

On Windows: %APPDATA%\Claude\claude_desktop_config.json

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "dataset-viewer": {
      "command": "uv",
      "args": [
        "run",
        "dataset-viewer"
      ]
    }
  }
}

Usage Examples

1. Validate a dataset:

{
  "dataset": "stanfordnlp/imdb"
}

2. Get dataset information:

{
  "dataset": "stanfordnlp/imdb"
}

3. Search dataset contents:

{
  "dataset": "stanfordnlp/imdb",
  "config": "plain_text",
  "split": "train",
  "query": "great movie"
}

4. Filter and sort rows:

{
  "dataset": "stanfordnlp/imdb",
  "config": "plain_text",
  "split": "train",
  "where": "label = 'positive'",
  "orderby": "text DESC",
  "page": 0
}

5. Get dataset statistics:

{
  "dataset": "stanfordnlp/imdb",
  "config": "plain_text",
  "split": "train"
}

License

MIT License - see LICENSE for details