# Dataset Viewer MCP Server

> Server interfacing with Hugging Face Dataset Viewer API for analyzing datasets without full downloads. Supports validation, info retrieval, row fetching, statistics, searching, filtering, and Parquet downloads.

- **URL:** https://github.com/privetin/dataset-viewer-mcp-server
- **Category:** Data Analysis & Exploration MCP Servers
- **Tags:** Open Source, Huggingface, Datasets
- **Updated:** 2026-04-23 17:02
- **Canonical page:** https://mcpserver.ever.works/th/items/dataset-viewer-mcp-server

## Details

## Tools
- `validate`: Checks if a dataset exists and is accessible.
- `get_info`: Retrieves detailed information about a dataset.
- `get_rows`: Gets paginated contents of a dataset.
- `get_first_rows`: Retrieves first few rows from a dataset split.
- `get_statistics`: Gets statistics about a dataset split.
- `search_dataset`: Searches for text within a dataset.
- `filter`: Filters rows using SQL-like conditions.
- `get_parquet`: Downloads entire dataset in Parquet format.

## External APIs and technologies
- Hugging Face Dataset Viewer API
- httpx: HTTP client
- Python 3.12+

## Configuration requirements
- `HUGGINGFACE_TOKEN` (optional): For private datasets.

---

_This Markdown mirror is generated by Ever Works for AI agents. The canonical HTML page is at https://mcpserver.ever.works/th/items/dataset-viewer-mcp-server._