# dataset-viewer

> MCP Server

This repository provides an MCP server that interacts with the Hugging Face Dataset Viewer API, enabling users to browse, analyze, search, and access datasets hosted on the Hugging Face Hub.

## Overview

- **Category:** AI
- **Language:** Python
- **Stars:** 31
- **Forks:** 6
- **Owner:** privetin
- **GitHub:** https://github.com/privetin/dataset-viewer
- **Created:** 2025-01-02T07:55:29+00:00
- **Updated:** 2025-03-25T12:12:15+00:00
- **Source:** https://model-context-protocol.com/servers/hugging-face-dataset-viewer-api-server

## Setup

## Setup

1. Clone the repository:
```bash
git clone https://github.com/privetin/dataset-viewer.git
cd dataset-viewer
```

2. Create a virtual environment and install:
```bash
# 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 .
```

## Tools

## Available Tools

1. **validate** (Check if a dataset exists and is accessible)
2. **get_info** (Get detailed information about a dataset)
3. **get_rows** (Get paginated contents of a dataset)
4. **get_first_rows** (Get first rows from a dataset split)
5. **get_statistics** (Get statistics about a dataset split)
6. **search_dataset** (Search for text within a dataset)
7. **filter** (Filter rows using SQL-like conditions)
8. **get_parquet** (Download entire dataset in Parquet format)