Hugging Face MCP Server

Hugging Face Official MCP Server connects your large language models (LLMs) to the Hugging Face Hub and thousands of Gradio AI Applications, enabling seamless MCP (Model Context Protocol) integration across multiple transports. It supports STDIO, SSE (to be deprecated but still commonly deployed), StreamableHTTP, and StreamableHTTPJson, with the Web Application allowing dynamic tool management and status updates. This MCP server is designed to be run locally or in Docker, and it provides integrations with Claude Desktop, Claude Code, Gemini CLI (and its extension), VSCode, and Cursor, making it easy to configure and manage MCP-enabled tools and endpoints. Tools such as hf_doc_search and hf_doc_fetch can be enabled to enhance document discovery, and an optional Authenticate tool can be included to handle OAuth challenges when called.

The MCP Server acts as a bridge between LLM clients and MCP-enabled endpoints, orchestrating tool availability and communication across multiple transports. It is capable of running in STDIO, SSE, Streamable HTTP, or JSON-mode HTTP, allowing flexible deployments from local development to production-grade configurations. The Web UI lets you switch tools on and off, and the server can automatically enable document-related tools when document search is enabled. Example deployment patterns include installing via Claude or Gemini CLI, or integrating with VSCode or Cursor for seamless tooling within development environments.

Key usage patterns from the documentation include:

npx @llmindset/hf-mcp-server       # Start in STDIO mode
npx @llmindset/hf-mcp-server-http  # Start in Streamable HTTP mode
npx @llmindset/hf-mcp-server-json  # Start in Streamable HTTP (JSON RPC) mode

docker pull ghcr.io/evalstate/hf-mcp-server:latest
docker run --rm -p 3000:3000 ghcr.io/evalstate/hf-mcp-server:latest

claude mcp add hf-mcp-server -t http https://huggingface.co/mcp?login

claude mcp add hf-mcp-server \
  -t http https://huggingface.co/mcp \
  -H "Authorization: Bearer <YOUR_HF_TOKEN>"

gemini mcp add -t http huggingface https://huggingface.co/mcp?login

gemini extensions install https://github.com/huggingface/hf-mcp-server

To configure VSCode manually, the example mcp.json snippet is shown as:

"huggingface": {
    "url": "https://huggingface.co/mcp",
    "headers": {
        "Authorization": "Bearer <YOUR_HF_TOKEN>"
    }

Similarly, Cursor users can install via a provided link and use a config snippet like:

"huggingface": {
    "url": "https://huggingface.co/mcp",
    "headers": {
        "Authorization": "Bearer <YOUR_HF_TOKEN>"
    }