Hugging Face MCP Server

Official Hugging Face MCP Server that connects AI assistants directly to the Hugging Face Hub ecosystem. Provides tools for searching and retrieving models, datasets, and research papers, running inference on thousands of Gradio-powered AI applications (Spaces), and accessing the full Hub API. Supports remote HTTP-streaming via https://huggingface.co/mcp with OAuth or Bearer token auth, as well as local stdio deployment. Works with Claude, Gemini CLI, VS Code, Cursor, and any MCP-compatible client.

{
  "mcpServers": {
    "huggingface": {
      "url": "https://github.com/huggingface/hf-mcp-server",
      "env": {
        "HF_TOKEN": "<YOUR_HF_TOKEN>"
      }
    }
  }
}

{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "task": {
      "type": "string",
      "description": "Filter by ML task (e.g. text-generation, image-classification)"
    },
    "limit": {
      "type": "integer",
      "description": "Maximum number of results (default 10)"
    },
    "query": {
      "type": "string",
      "description": "Search query (e.g. \"text classification\", \"llama\", \"whisper\")"
    },
    "library": {
      "type": "string",
      "description": "Filter by framework (e.g. transformers, diffusers)"
    },
    "language": {
      "type": "string",
      "description": "Filter by language code (e.g. en, fr, zh)"
    }
  }
}

{
  "type": "object",
  "required": [
    "modelId"
  ],
  "properties": {
    "modelId": {
      "type": "string",
      "description": "Model ID in the format \"owner/model-name\" (e.g. \"meta-llama/Llama-3.1-8B\")"
    }
  }
}

{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "task": {
      "type": "string",
      "description": "Filter by task category"
    },
    "limit": {
      "type": "integer",
      "description": "Maximum number of results (default 10)"
    },
    "query": {
      "type": "string",
      "description": "Search query"
    }
  }
}

{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "description": "Maximum number of results (default 10)"
    },
    "query": {
      "type": "string",
      "description": "Search query (e.g. \"mixture of experts\", \"RLHF\")"
    }
  }
}

{
  "type": "object",
  "required": [
    "modelId",
    "inputs"
  ],
  "properties": {
    "inputs": {
      "type": "string",
      "description": "Input text, prompt, or data for the model"
    },
    "modelId": {
      "type": "string",
      "description": "Model ID to run inference on"
    },
    "parameters": {
      "type": "object",
      "description": "Optional model-specific parameters (e.g. max_new_tokens, temperature)"
    }
  }
}

{
  "type": "object",
  "properties": {
    "sdk": {
      "type": "string",
      "description": "Filter by SDK (gradio, streamlit, docker)"
    },
    "limit": {
      "type": "integer",
      "description": "Maximum number of results (default 10)"
    },
    "query": {
      "type": "string",
      "description": "Search query for spaces"
    }
  }
}