{
  "entry": {
    "kind": "mcp",
    "slug": "hugging-face-mcp-server",
    "name": "Hugging Face MCP Server",
    "vendor": "Hugging Face",
    "description": "Hugging Face's official server exposes models, datasets, Spaces, and inference to agents, so an assistant can search the hub, read model cards, and call hosted inference endpoints as tools.\n\nCapabilities are outbound network access and credential access for the hub token. The supply-chain angle is the one to think about: an agent that can discover and invoke arbitrary community models and Spaces is an agent whose behaviour depends on artifacts nobody on your team reviewed. Model cards and dataset descriptions are also free text reaching the model's context. Prefer allow-listing the models an assistant may call over granting open hub access.",
    "website": "https://huggingface.co/docs/hub/en/mcp",
    "repository": null,
    "documentationUrl": "https://huggingface.co/docs/hub/en/mcp",
    "license": null,
    "version": null,
    "trustLevel": "official",
    "capabilities": [
      "network:outbound",
      "credentials:access"
    ],
    "packaging": null,
    "configFiles": null,
    "category": null,
    "updatedAt": "2026-09-02",
    "risk": {
      "score": 20,
      "band": "low",
      "signals": [
        {
          "id": "trust-official",
          "kind": "trust",
          "label": "Published by the vendor",
          "contribution": -40
        },
        {
          "id": "high-risk-capabilities",
          "kind": "capability",
          "label": "1 high-risk capability: credentials:access",
          "contribution": 10
        }
      ],
      "dangerousCombos": []
    },
    "dangerousCombos": []
  }
}