Hugging Face 推出官方 MCP 伺服器：讓 AI 助理直接存取 Hub 模型與資料集
Original: Building the Hugging Face MCP Server
Hugging Face has officially announced the launch of its dedicated MCP (Model Context Protocol) server — a major step in ecosystem…
Hugging Face 宣布推出其 Model Context Protocol (MCP) 伺服器。這項工具讓支援 MCP 的 AI 客戶端（如 Claude Desktop、Cursor）能夠直接與 Hugging Face Hub 互動。使用者可以直接在對話中搜尋熱門模型、查詢資料集結構與讀取 Model Card，大幅簡化了 AI 開發者與研究人員的工作流程。
Hugging Face has officially announced the launch of its dedicated MCP (Model Context Protocol) server — a major step in ecosystem integration. The Model Context Protocol (MCP) is an open standard introduced by Anthropic to solve the problem of fragmented connectivity between large language models (LLMs) and external data sources, tools, and APIs. With the Hugging Face MCP Server, developers can now allow MCP-compatible AI clients — such as Claude Desktop, Cursor, and other development tools — to interact deeply and directly with the Hugging Face Hub.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Hugging Face Blog →Summaries are AI-generated; the original article is authoritative.