co.huggingface/hf-mcp-server

Est-ce que co.huggingface/hf-mcp-server est sûr ?

Au dernier audit MCP Hub, le serveur MCP « co.huggingface/hf-mcp-server » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 4 outils

• hf_fs≈ 2364 tokens

  When to use: Hugging Face Hub models, datasets, Spaces, collections, papers, daily papers, today's trending models, current paper leaderboard, docs, and repository files. Examples: {"operations":[{"cmd":"ls","args":["hf://models/trending","--limit","10"]}]} {"operations":[{"cmd":"ls","args":["hf://papers/trending"]}]} {"operations":[{"cmd":"ls","args":["hf://papers/daily/latest"]}]} {"operations":[{"cmd":"cat","args":["hf://papers/2501.00001/paper.md"]}]} {"operations":[{"cmd":"search","args":["hf://models","--tag","base_model:finetune:org/repo"]}]} Use hf_fs for Hugging Face Hub filesystem operations. Call it with operations, an array of {cmd, args} items; multiple operations may be submitted together. Usage: {"operations":[{"cmd":"ls","args":["hf://models/org/repo"]}]} Grammar; each string below is one args array item: ls URI [--recursive] [--glob GLOB] [--type TYPE] [--sort SORT] [--limit N] cat URI [--offset N] [--max-bytes N] attach URI [--max-bytes N] stat URI find URI [--name GLOB] [--path GLOB] [--type TYPE] [--limit N] search URI [QUERY] [--type TYPE] [--sort SORT] [--tag TAG] [--kind mcp] [--limit N] COMMAND = ls|cat|attach|stat|find|search. TYPE = file|dir|repo|bucket|collection|paper|link. SORT = createdAt|downloads|likes|lastModified|likes30d|trendingScore|mainSize|id|trending|upvotes. URI is a canonical hf:// URI. QUERY and GLOB are each one string. Use search for resource discovery, not repository-content search; ls for a known directory, find for recursive file discovery by name/path (not file contents), stat for filesystem metadata or an uncertain target type, cat for text contents, and attach for a complete JPEG, PNG, or WebP image. When the request gives an exact text-file URI, use cat directly; do not add ls or stat first. stat does not read the contents of JSON, Markdown, or other text files. Search scopes: hf://models[/OWNER], hf://datasets[/OWNER], hf://spaces[/OWNER], hf://collections[/OWNER], hf://papers, and hf://docs[/...]. Repository and repository-file scopes are not supported: search a resource root or owner scope to discover resources; use find for file discovery within a repository or cat for a known text file. Paper and documentation search require QUERY. --tag filters models, datasets, and Spaces by Hub tag (repeatable; all must match) and applies only to hf://models|datasets|spaces[/OWNER]; omit QUERY when the tag already identifies the target, because QUERY also filters repository names. Derived models carry base_model:ID and base_model:RELATION:ID tags, where RELATION is finetune, adapter, merge, or quantized. --kind applies only to hf://spaces[/OWNER]; the only valid --kind value is mcp, which selects MCP Spaces. Tag families are documented at hf://README.md. Use ls hf://models/trending, hf://datasets/trending, hf://spaces/trending, or hf://papers/trending for trending listings. hf://papers/ID is a paper directory, not paper text. Use cat hf://papers/ID/paper.md for paper text and cat hf://papers/ID/metadata.json for metadata. No preliminary listing is needed for these known paths. Use ls hf://papers/ID to discover other resources. Omit --limit, --sort, and --type unless the request requires them. Limits and path-specific behavior are documented at hf://README.md. Issue one hf_fs call.

  Paramètres, retour & exemple (1)

  Paramètres

  • operations · array · requis

  Exemple d'appel

  {"name": "hf_fs", "arguments": {"operations": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"results": [], "truncated": true, "truncation_reason": "texte"}}

• hf_whoami≈ 1842 tokens

  Inspect the current Hugging Face authentication context, including the account, visible organization memberships, and credential access details. Read-only and never returns credential values.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "hf_whoami", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• hub_repo_details≈ 520 tokens

  Get details for one or more Hugging Face repos (model, dataset, or space). Auto-detects type unless specified. For datasets, use operations: overview, dataset_structure, dataset_preview. Use dataset_structure first to discover configs, splits, sizes, and schema. Use dataset_preview only when config and split are known, unless the dataset has a single config/split.

  Paramètres, retour & exemple (7)

  Paramètres

  • limit · integer · optionnel
    Row count for dataset_preview. Defaults to 5 and is clamped to 1-100.
  • split · string · optionnel
    Dataset Viewer split. Required for dataset_preview when the dataset has multiple config/split options. Discover via dataset_structure.
  • config · string · optionnel
    Dataset Viewer config. Required for dataset_preview when the dataset has multiple config/split options. Discover via dataset_structure.
  • offset · integer · optionnel
    Row offset for dataset_preview. Defaults to 0.
  • repo_ids · array · requis
    Repo IDs for (models|dataset/space) - usually in author/name format (e.g. openai/gpt-oss-120b)
  • repo_type · string · optionnel · model | dataset | space
    Specify lookup type; otherwise auto-detects
  • operations · array · optionnel
    Details to return. Defaults to ["overview"]. For datasets, prefer ["overview", "dataset_structure"] first; then call ["dataset_preview"] with config and split.

  Exemple d'appel

  {"name": "hub_repo_details", "arguments": {"repo_ids": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• hub_repo_search≈ 413 tokens

  Search Hugging Face repositories with a shared query interface. You can target models, datasets, spaces, or aggregate across multiple repo types in one call. Include links to repositories in your response.

  Paramètres, retour & exemple (6)

  Paramètres

  • sort · string · optionnel · trendingScore | downloads | likes | createdAt | lastModified
    Sort order (descending): trendingScore, downloads, likes, createdAt, lastModified
  • limit · number · optionnel
    Maximum number of results to return per selected repo type
  • query · string · optionnel
    Search term. Leave blank and specify sort + limit to browse trending or recent repositories.
  • author · string · optionnel
    Organization or user namespace to filter by (e.g. 'google', 'meta-llama', 'huggingface').
  • filters · array · optionnel
    Optional hub filter tags. Applied to each selected repo type (e.g. ["text-generation"], ["language:en"], ["mcp-server"]).
  • repo_types · array · optionnel
    Repository types to search. Defaults to ["model", "dataset"]. space uses keyword search via /api/spaces.

  Exemple d'appel

  {"name": "hub_repo_search", "arguments": {"sort": "trendingScore", "limit": 1, "query": "texte", "author": "texte", "filters": [], "repo_types": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://huggingface.co/mcp