Hugging Face MCP 服务器

Transformers

Provides state-of-the-art machine learning models for text, computer vision, audio, video, and multimodal tasks, supporting inference and training across PyTorch, TensorFlow, and JAX.

vLLM

Provides a high-throughput and memory-efficient inference and serving engine for large language models.

JARVIS

Connects large language models (LLMs) with a vast array of expert AI models to solve complex tasks.

Trackio

Provides a lightweight, local-first experiment tracking solution for machine learning models, offering a `wandb`-compatible API for seamless integration.

Dingo

Automatically detect and evaluate data quality issues across diverse datasets and modalities.

Hfspace

Connects to Hugging Face Spaces to provide image generation, vision model, text-to-speech, and other capabilities to Claude Desktop with minimal setup.

Hugging Face

Provides a flexible server and web application for deploying Hugging Face Hub API and search endpoints.

Academia

Automate scientific research workflows by providing tools to search, fetch, analyze, and report on academic papers and datasets.

Hugging Face

Enables Large Language Models to interact with and retrieve information from Hugging Face's models, datasets, and other resources.

Knowledge Base

Retrieves and lists content from various knowledge bases using semantic search.

Safe Local Python Executor

Executes Python code generated by LLMs in a secure, locally-hosted environment, leveraging Hugging Face's LocalPythonExecutor and MCP for LLM application integration.

Dataset Viewer

Provides access to browse, filter, analyze, and download datasets hosted on the Hugging Face Hub.

OpenGenes

Provides a standardized interface to access aging and longevity research data for AI systems through the Model Context Protocol (MCP).

Hugging Face Hub Semantic Search

Provides AI-powered semantic search and discovery capabilities for Hugging Face models and datasets via a Model Context Protocol server.

I18n Agent

Automates internationalization and localization workflows using AI, specifically for documentation projects integrated within GitHub Actions.

Files-DB

Provides LLM coding agents with vector search capabilities for software projects via the Message Control Protocol (MCP).

RAG

Implements a Python-based server for Retrieval-Augmented Generation (RAG) workflows, managing context, tool invocation, and model output for clients like Claude Desktop.

Huggingfetch

Accelerates HuggingFace model downloads and integrates them into various AI development clients.

Rag Pipeline Research

Explores Retrieval-Augmented Generation (RAG) and Multi-Cloud Processing (MCP) server integration using free and open-source models.

AgentIndex

Discover and query AI agents by capability through a comprehensive, machine-first index.