"Hugging Face" matching MCP servers:

Supercharges Claude Desktop with persistent semantic memory, sandboxed file I/O, live web search, and local emotional intelligence using a local ChromaDB and Hugging Face model.

Enables searching a combined catalog of Fontshare, Fontsource, and Google fonts, inspecting family metadata and variable axes, then downloading self-hosted woff2 files and generating matching @font-face CSS rules.

A local RAG server that enables document indexing and sentence window retrieval across multiple file formats like PDF, MD, and DOCX. It supports both local Hugging Face models and OpenAI embeddings for efficient context-aware querying through the Model Context Protocol.

A universal Model Context Protocol server in Java, enabling interaction with multiple LLMs (OpenAI, Gemini, Hugging Face) and databases (MongoDB) through a modular Spring Boot architecture.

Enables MCP clients and AI agents to read and query semantic PMI/GD&T from local STEP AP242 files, including characteristic lists, datum reference frames, per-face tolerances, data-quality warnings, and exports to CSV, JSON, or ballooned PDF reports.

Enables agents to download single model weight files from Hugging Face repositories or Civitai model versions directly into allowlisted ComfyUI model folders. Source identifiers, destination categories, and file extensions are validated, and existing files are never overwritten.