get_dataset_splitsLABSCO SUMMARY
Decide whether a dataset is worth downloading before you download it.
Everything here runs against the Dataset Viewer API, so you can preview rows, check statistics, run a filter and look for PII entities on a multi-gigabyte dataset without pulling a byte of it locally. The PII and opt-in/opt-out tools are the ones that are hard to replicate by hand, and they are the reason to reach for this before a training run rather than after.
What it is
A FastMCP server over the Hugging Face Dataset Viewer API, implementing all of its GET endpoints so a client can inspect Hub datasets remotely.
What you get
- Structure:
get_dataset_splits,get_dataset_infofor metadata and features, andget_dataset_size - Rows:
get_dataset_first_rowsfor a preview of the first 100, andget_dataset_rowsfor paginated access - Finding things:
search_datasetfor full-text search inside a dataset, andfilter_datasetfor SQL-like filtering - Quality checks:
get_dataset_statisticsandcheck_dataset_validity - Files and compliance:
get_dataset_parquet,get_dataset_opt_in_out_urls, andget_dataset_presidio_entitiesfor PII entity detection - 12 tools in total, one per API endpoint, so nothing is hidden behind a generic call
Requirements
Python 3.12+ and uv for local development, or build the container with make docker-build and let the client run huggingface-mcp:latest with docker run --rm -i. Copy .env.example to .env if you need to configure anything.
Setup effort
One command — docker run --rm -i --name huggingface-mcp-claude huggingface-mcp:latest
USE CASES
01
Sizing up a dataset you just found
Check the splits, info and size, then preview the first rows before deciding anything.
02
Checking for personal data
Run the PII entity detection and the opt-in/opt-out URL listing before using the data.
03
Finding the rows you actually need
Search the dataset full-text, or apply a SQL-like filter, instead of paging through everything.
12 tools
Listed in project docs. Your client may show a different list.
get_dataset_infoget_dataset_first_rowsget_dataset_rowssearch_datasetget_dataset_sizeget_dataset_statisticsfilter_datasetcheck_dataset_validityget_dataset_parquetget_dataset_opt_in_out_urlsget_dataset_presidio_entitiesBEFORE YOU INSTALL
What to know first
Tools you get
12 tools named in the project's documentation.
Requires
- docker on PATH
- Python 3.12+
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
docker run --rm -i --name huggingface-mcp-claude huggingface-mcp:latestMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"huggingface-mcp": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"--name",
"huggingface-mcp-claude",
"huggingface-mcp:latest"
]
}
}
}
