huggingface_mcp

Talos-Data-Consulting/huggingface_mcp

3.2

If you are the rightful owner of huggingface_mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

The Hugging Face MCP Server provides access to the Hugging Face Dataset Viewer API, allowing users to query, explore, and analyze datasets from the Hugging Face Hub.

Tools

  1. get_dataset_splits

    Dataset splits information

  2. get_dataset_info

    Dataset metadata and features

  3. get_dataset_first_rows

    Preview first 100 rows

  4. get_dataset_rows

    Paginated data access

  5. search_dataset

    Full-text search within datasets

  6. get_dataset_size

    Dataset size information

  7. get_dataset_statistics

    Statistical analysis

  8. filter_dataset

    SQL-like data filtering

  9. check_dataset_validity

    Dataset validation

  10. get_dataset_parquet

    Parquet file information

  11. get_dataset_opt_in_out_urls

    Opt-in/out URLs

  12. get_dataset_presidio_entities

    PII entity detection

Hugging Face MCP Server

MCP server providing access to the Hugging Face Dataset Viewer API. Query datasets, explore data, search content, and analyze statistics from the Hugging Face Hub's extensive collection of machine learning datasets.

Features

  • 12 MCP Tools covering all API endpoints:
    • get_dataset_splits - Dataset splits information
    • get_dataset_info - Dataset metadata and features
    • get_dataset_first_rows - Preview first 100 rows
    • get_dataset_rows - Paginated data access
    • search_dataset - Full-text search within datasets
    • get_dataset_size - Dataset size information
    • get_dataset_statistics - Statistical analysis
    • filter_dataset - SQL-like data filtering
    • check_dataset_validity - Dataset validation
    • get_dataset_parquet - Parquet file information
    • get_dataset_opt_in_out_urls - Opt-in/out URLs
    • get_dataset_presidio_entities - PII entity detection

Quick Start

Claude Desktop Integration

Add to your Claude Desktop claude_desktop_config.json:

{
  "mcpServers": {
    "huggingface-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "--name", "huggingface-mcp-claude",
        "huggingface-mcp:latest"
      ]
    }
  }
}

Build Docker Image

make docker-build

Development

Prerequisites

  • Python 3.12+
  • uv

Setup

make install    # Install dependencies
make test       # Run tests (38 tests)
make example    # Test all tools
make run        # Start server directly

Docker Commands

make docker-build    # Build image
make docker-run      # Run container
make docker-stop     # Stop container

API Coverage

Implements all GET endpoints from the Hugging Face Dataset Viewer API:

EndpointToolDescription
/splitsget_dataset_splitsDataset splits information
/infoget_dataset_infoDataset metadata and features
/first-rowsget_dataset_first_rowsPreview first 100 rows
/rowsget_dataset_rowsPaginated data access
/searchsearch_datasetFull-text search within datasets
/sizeget_dataset_sizeDataset size information
/statisticsget_dataset_statisticsStatistical analysis
/filterfilter_datasetSQL-like data filtering
/is-validcheck_dataset_validityDataset validation
/parquetget_dataset_parquetParquet file information
/opt-in-out-urlsget_dataset_opt_in_out_urlsOpt-in/out URLs
/presidio-entitiesget_dataset_presidio_entitiesPII entity detection

Built with FastMCP following all development best practices.

Configuration

Copy the example environment file and configure as needed:

cp .env.example .env
# Edit .env with your configuration

Usage

Running the Server

make run

Running Tests

make test

Running Examples

make example

Docker

Build and Run

make docker-build
make docker-run

With Docker Compose

docker-compose up --build

Development

TODO: Add development guidelines

API Documentation

TODO: Add API documentation

Contributing

TODO: Add contributing guidelines

License

TODO: Add license information