dataset-viewer
The Dataset Viewer MCP Server is designed to interact with the Hugging Face Dataset Viewer API, allowing for the browsing and analysis of datasets hosted on the Hugging Face Hub. It supports various dataset operations including statistics, searching, and filtering, with tools for detailed dataset management.
What is the purpose of the Dataset Viewer MCP Server?
The server is designed to interact with the Hugging Face Dataset Viewer API, allowing users to browse, analyze, and manage datasets hosted on the Hugging Face Hub.
How does the server handle private datasets?
The server supports authentication for private datasets using the Hugging Face API token, which can be set as an environment variable.
What are the prerequisites for setting up the server?
You need Python 3.12 or higher and the 'uv' package installer to set up the server.
Can I search and filter dataset contents?
Yes, the server provides tools for searching and filtering dataset contents using SQL-like conditions.
Is there a way to download datasets in a specific format?
Yes, the server allows downloading entire datasets in Parquet format.