"Hugging Face" matching MCP servers:

An unofficial MCP server that provides semantic search capabilities for Hugging Face models and datasets, enabling Claude and other MCP-compatible clients to search, discover, and explore the Hugging Face ecosystem using natural language queries.

An MCP server that turns the Hugging Face Hub into a conversational model picker with a tool-use eval harness to prove the agent actually uses it correctly.

Enables face keypoint detection, beautification, age/gender transform, face swap, cartoonization, and liveness detection via AceDataCloud API.

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.

Generates realistic human face images that don't represent real people, offering various output shapes, configurable dimensions, and batch generation capabilities.

Gives Claude Code, Cursor and other agents structural awareness of a PyTorch model: layers, params, FLOPs, blast radius, the design linter, a full readiness/cost/deployment verdict, and a ranker for which of k candidate designs to train. Reads a .py, a .neurarch.json, 81 bundled reference architectures, or a Hugging Face repo. Offline, no API key.

Provides multi-provider image generation with automatic fallback across services like Pollinations.ai, Cloudflare, and Hugging Face. It features specialized pixel art generation, cost tracking, and automatic saving of generated visual assets to disk.

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.

Connects LLMs to the Hugging Face Hub and thousands of Gradio AI applications, enabling repository search, file access, Space interaction, jobs, and sandbox tools through MCP. Supports STDIO and Streamable HTTP transports with optional Hugging Face authentication.

Enables searching, fetching, and analyzing scientific papers from ArXiv, ACL Anthology, Semantic Scholar, and Hugging Face datasets, with optional LLM-powered document QA and research proposal workflows.

FaceTron is a high-performance face embedding server with ONNX Runtime, dynamic multi-model loading, and MCP-compatible OpenAPI metadata for offline face recognition and detection.

An MCP server that generates 2D and 3D game assets from text prompts using AI models from Hugging Face Spaces, allowing developers to easily create game art through Claude Desktop or other MCP clients.

Enables management of local video datasets with directory browsing and direct upload capabilities to Hugging Face Hub repositories. Supports video file validation, batch uploads, and automated dataset repository creation with secure authentication.

A boilerplate for building and deploying MCP servers on Vercel, featuring example tools like greeting, calculator, weather, and Hugging Face image generation.

A boilerplate project for quickly developing Model Context Protocol (MCP) servers using TypeScript SDK, featuring example tools (calculator, greet), resources (server info), and AI image generation capabilities via Hugging Face.

Personal finance calculators exposed as an MCP server with a Gradio UI, deployable to Hugging Face Spaces.

Enables searching and browsing the Ace Achievers course catalog and question bank with tiered hint reveals.

Provides 8 financial-grade KYC identity verification tools for AI agents, including face comparison, liveness detection, document OCR, and risk media labeling.

A Model Context Protocol server for the PicDefense.io API — let AI agents run reverse-image risk analysis, EXIF extraction, image backlink discovery, and image content detection (face / landmark / logo / label / SafeSearch) on any image URL.

Implements Agentic Context Engineering to create self-improving AI coding assistants that learn from execution feedback and build persistent knowledge playbooks. Reduces token usage by 86.9% while improving code accuracy by 10.6% through incremental context updates.