Hugging Face
About
Access the Hugging Face Dataset Viewer API to query, explore, search, and analyze machine learning datasets from the Hugging Face Hub.
Details
- Author
- talos-data-consulting
- Categories
- Cloud Service, AI, Other, Knowledge Base
Jump to
Setup
Install Hugging Face in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/talos-data-consulting/huggingface_mcp
Follow the installation instructions in the repository README, then restart your MCP client.
MCP server providing access to theHugging 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.
- 12 MCP Toolscovering 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
Add to your Claude Desktopclaude_desktop_config.json:
{ "mcpServers": { "huggingface-mcp": { "command": "docker", "args": [ "run", "--rm", "-i", "--name", "huggingface-mcp-claude", "huggingface-mcp:latest" ] } } }
make install # Install dependencies make test # Run tests (38 tests) make example # Test all tools make run # Start server directly
make docker-build # Build image make docker-run # Run container make docker-stop # Stop container
Implements all GET endpoints from theHugging Face Dataset Viewer API:
Built withFastMCPfollowing all development best practices.
Copy the example environment file and configure as needed:
cp .env.example .env # Edit .env with your configuration
An MCP server for interacting with Dappier's Retrieval-Augmented Generation (RAG) models.
Free oncology data (research, clinical trials, FDA approvals, news) plus IBM MAMMAL biomedical predictions, exposed as MCP tools.
Open compute-pricing reference — daily GPU and inference-token medians, free under CC-BY 4.0.
An MCP server for Snowflake providing tools for Cortex AI features like Search, Analyst, and Complete.
Get access to Kaggle's datasets, models, competitions, notebook and benchmarks.
Multimodal RAG for source-backed AI answers
A server for Retrieval-Augmented Generation (RAG) using the Contextual AI platform.
Investment analysis for 2,260+ US equities — 43 tools for stock screening, ML earnings predictions, insider/congressional trades, macro signals, Fear & Greed, and alternative data.
An MCP server for Hierarchical Event Descriptors (HED) that automates sidecar creation and annotation for BIDS event files using LLMs.
Daily Scandinavian AI benchmark — Norwegian, Swedish, Danish. 12+ models tested.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
