Hugging Face is an AI community building the future. They provide tools that enable users to build, train and deploy ML models based on open source code and technologies.
JavaScript implementation of MiniMax MCP that enables interaction with MiniMax AI services for image generation, video generation, text-to-speech, and voice cloning through MCP-compatible clients.
Last updated
10
396
122
MIT
Why this server?
Downloads embedding models from Hugging Face for local ONNX inference, enabling dense reranking of search results.
Shrink the web for your local LLMs! Provides web research capabilities to low resource models and environments.
Last updated
2
1
32
MIT
Why this server?
Automatically downloads the latest OpenGenes database and documentation from Hugging Face Hub, ensuring access to up-to-date aging and longevity research data without manual file management
Provides standardized access to aging and longevity research data from the OpenGenes database, enabling AI assistants to query comprehensive biomedical datasets through SQL and structured interfaces.
Last updated
3
17
MIT
Why this server?
Allows interaction with the Hugging Face Dataset Viewer API, providing tools for browsing, searching, filtering, and analyzing datasets hosted on the Hugging Face Hub, along with support for authentication for private datasets.
Enables interaction with the Hugging Face Dataset Viewer API, allowing users to browse, search, filter, and analyze datasets hosted on the Hugging Face Hub.
Last updated
8
31
MIT
Why this server?
Allows searching Hugging Face for available MLX models and downloading them locally to cache before launching.
An MCP server to autonomously launch, manage, and shutdown local mlx-lm instances on Apple Silicon.（Apple Silicon上でローカルLLM (mlx-lm) を自律的に起動・管理・停止するためのMCPサーバー。）
Last updated
8
1
Apache 2.0
Why this server?
Uses Hugging Face's sentence transformers API to generate embeddings for semantic search in the RAG system, specifically leveraging the sentence-transformers/all-MiniLM-L6-v2 model for document and memory vectorization
A complete MCP server for Retrieval-Augmented Generation with file management and vector memory for agents. Supports multiple document formats (PDF, DOCX, TXT, MD, CSV, JSON) with semantic search using Hugging Face embeddings and ChromaDB for efficient vector storage.
Last updated
11
4
1
MIT
Why this server?
Supports automated ingestion of daily papers from Hugging Face via the pipeline function, which evaluates relevance, generates embeddings, deduplicates content, and integrates them into the knowledge base.
Provides unified access to 100+ AI models from OpenAI, Anthropic, Google, AWS Bedrock and other providers through a single MCP interface. Enables seamless switching between different AI models using LiteLM's unified API without requiring separate integrations for each provider.
Last updated
3
7
MIT
Why this server?
Integrates with Hugging Face APIs to access the TSpec-LLM dataset containing 535M words of 3GPP specification data for direct specification search and analysis
Enables AI assistants to access and search 3GPP telecommunications specifications through direct integration with the TSpec-LLM dataset. Provides real-time specification content, implementation requirements, and multi-spec comparisons for 3GPP standards development.
