"Hugging Face" matching MCP servers:

Provides MCP tools for scanning, redacting, and packaging dataset/model directories for public release, leveraging Presidio for PII detection and generating Hugging Face cards and EU AI Act training-data summaries.

Exposes safe JSON contracts for validating and preparing datasets, running supervised fine-tuning, preference learning, RL, distillation, and evaluation, and managing checkpoints and exports through the Tinker SDK and Cookbook. It lets agents discover models and Hugging Face datasets, plan and execute training recipes, compare experiments, and export selected models.

Enables AI agents to import datasets from Hugging Face or Parquet, CSV, JSON, JSONL and DuckDB sources, map them onto a user-defined schema with per-row metadata, then preview, sample and write the converted rows into DuckDB files. Also exposes schema management, split lookup and target listing so an entire conversion pipeline can run in one call.

Provides a secure, policy-driven read-only gateway that exposes multiple databases to AI tools via MCP, with governed select, search, and aggregate operations and no free-form SQL.