Hugging Face MCP · Hugging Face

Operational

Unclaimed — claim this pagedeveloper-tools Streamable HTTP2025-06-18 API key expected

https://huggingface.co/mcp Docs

Badge

100%

Availability · 30 days · 356 checks

43 ms

Latency (last observation)

rev 4

Contract

27days

Schema stable

Incidents · 30 days

Aug 6, 2026

Observed since

Availability — last 30 days

No failures Some failures Mostly failing Auth required No observations

Last observed 1 h ago by MCP Tools Edge Scanner · scheduled every 120 min

Server version changed Informational Sep 16, 2026 — 1:55 PM

Server reports version 0.4.20 (was 0.4.19).

Verifiedinitialize returned serverInfo.version 0.4.20.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Server version changed Informational Sep 10, 2026 — 7:40 PM

Server reports version 0.4.19 (was 0.4.18).

Verifiedinitialize returned serverInfo.version 0.4.19.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Descriptions or metadata changed Informational Sep 10, 2026 — 7:40 PM

1 description/metadata change; the functional contract is unchanged (hash sha256:5575083c8b77e527…).

VerifiedDescriptions or metadata for hf_fs changed.

InterpretationNo structural change. Wording changes can still influence model tool selection.

Path	Change	Classification	Detail
tools.hf_fs	description changed	Informational	Descriptions or metadata for `hf_fs` changed. No structural change. Wording changes can still influence model tool selection.

Observed by MCP Tools Edge Scanner

Server version changed Informational Sep 9, 2026 — 11:25 AM

Server reports version 0.4.18 (was 0.4.15).

Verifiedinitialize returned serverInfo.version 0.4.18.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Descriptions or metadata changed Informational Sep 9, 2026 — 11:25 AM

1 description/metadata change; the functional contract is unchanged (hash sha256:5575083c8b77e527…).

VerifiedDescriptions or metadata for hf_fs changed.

InterpretationNo structural change. Wording changes can still influence model tool selection.

Path	Change	Classification	Detail
tools.hf_fs	description changed	Informational	Descriptions or metadata for `hf_fs` changed. No structural change. Wording changes can still influence model tool selection.

Observed by MCP Tools Edge Scanner

Server version changed Informational Aug 26, 2026 — 8:55 PM

Server reports version 0.4.15 (was 0.4.14).

Verifiedinitialize returned serverInfo.version 0.4.15.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Descriptions or metadata changed Informational Aug 26, 2026 — 8:55 PM

1 description/metadata change; the functional contract is unchanged (hash sha256:5575083c8b77e527…).

VerifiedDescriptions or metadata for hf_fs changed.

InterpretationNo structural change. Wording changes can still influence model tool selection.

Path	Change	Classification	Detail
tools.hf_fs	description changed	Informational	Descriptions or metadata for `hf_fs` changed. No structural change. Wording changes can still influence model tool selection.

Observed by MCP Tools Edge Scanner

Server version changed Informational Aug 26, 2026 — 2:40 PM

Server reports version 0.4.14 (was 0.4.13).

Verifiedinitialize returned serverInfo.version 0.4.14.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Server version changed Informational Aug 25, 2026 — 11:35 AM

Server reports version 0.4.13 (was 0.4.12).

Verifiedinitialize returned serverInfo.version 0.4.13.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Descriptions or metadata changed Informational Aug 25, 2026 — 11:35 AM

1 description/metadata change; the functional contract is unchanged (hash sha256:5575083c8b77e527…).

VerifiedDescriptions or metadata for hf_fs changed.

InterpretationNo structural change. Wording changes can still influence model tool selection.

Path	Change	Classification	Detail
tools.hf_fs	description changed	Informational	Descriptions or metadata for `hf_fs` changed. No structural change. Wording changes can still influence model tool selection.

Observed by MCP Tools Edge Scanner

Server version changed Informational Aug 21, 2026 — 8:06 PM

Server reports version 0.4.12 (was 0.4.11).

Verifiedinitialize returned serverInfo.version 0.4.12.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Server version changed Informational Aug 21, 2026 — 9:41 AM

Server reports version 0.4.11 (was 0.4.10).

Verifiedinitialize returned serverInfo.version 0.4.11.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Breaking contract changes (32) Breaking Aug 21, 2026 — 9:41 AM

27 breaking, 3 potentially breaking, 1 non-breaking changes. Required parameter operations was added at hf_fs.inputSchema.

VerifiedRequired parameter operations was added at hf_fs.inputSchema.

InterpretationExisting calls that omit operations may fail schema validation.

Raw event details

{
  "beforeRev": 3,
  "afterRev": 4,
  "changeCount": 32
}

View full diff Observed by MCP Tools Edge Scanner

Server version changed Informational Aug 20, 2026 — 2:56 PM

Server reports version 0.4.10 (was 0.4.9).

Verifiedinitialize returned serverInfo.version 0.4.10.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Server version changed Informational Aug 14, 2026 — 1:15 PM

Server reports version 0.4.9 (was 0.4.8).

Verifiedinitialize returned serverInfo.version 0.4.9.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Potentially breaking contract changes (8) Potentially breaking Aug 14, 2026 — 1:15 PM

1 potentially breaking, 3 non-breaking changes. Schema composition (allOf) at hf_fs.outputSchema changed.

VerifiedSchema composition (allOf) at hf_fs.outputSchema changed.

InterpretationThe accepted shape changed in a way that requires manual review; some existing calls may no longer validate.

Raw event details

{
  "beforeRev": 2,
  "afterRev": 3,
  "changeCount": 8
}

View full diff Observed by MCP Tools Edge Scanner

Server version changed Informational Aug 12, 2026 — 1:20 PM

Server reports version 0.4.8 (was 0.4.7).

Verifiedinitialize returned serverInfo.version 0.4.8.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Server version changed Informational Aug 12, 2026 — 11:15 AM

Server reports version 0.4.7 (was 0.4.8).

Verifiedinitialize returned serverInfo.version 0.4.7.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Server version changed Informational Aug 11, 2026 — 12:20 PM

Server reports version 0.4.8 (was 0.4.7).

Verifiedinitialize returned serverInfo.version 0.4.8.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Server version changed Informational Aug 7, 2026 — 2:41 PM

Server reports version 0.4.7 (was 0.4.6).

Verifiedinitialize returned serverInfo.version 0.4.7.

InterpretationVersion changes often accompany contract or behavior changes; drift detection will confirm.

Observed by MCP Tools Edge Scanner

Non-breaking contract changes (2) Non-breaking Aug 7, 2026 — 2:41 PM

1 non-breaking change. Tool hf_whoami now declares an output schema.

VerifiedTool hf_whoami now declares an output schema.

InterpretationA new guarantee for consumers.

Raw event details

{
  "beforeRev": 1,
  "afterRev": 2,
  "changeCount": 2
}

View full diff Observed by MCP Tools Edge Scanner

Baseline captured Aug 6, 2026 — 5:10 AM

4 tools, 155 resources, 0 prompts observed. Future observations will identify outages, recoveries, protocol changes, and contract drift from this state.

VerifiedCanonical contract hash sha256:44726c061eb0bc84… computed from the normalized capability inventory.

Raw event details

{
  "contractHash": "sha256:44726c061eb0bc84805b44f046ecf47d3c9d5832db4d2fa03093e6450b121438"
}

Observed by MCP Tools Edge Scanner

Advertised capabilities

Tools · 4 Resources · 155 Prompts Logging Completions Experimental

Tools 4

hf_whoami 0 params Inspect the current Hugging Face authentication context, including the account, visible organization membershi…

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

Input schema

No parameters.

Output schema

No parameters.

Raw schema JSON

hf_whoami — raw

{
  "name": "hf_whoami",
  "description": "Inspect the current Hugging Face authentication context, including the account, visible organization memberships, and credential access details. Read-only and never returns credential values.",
  "inputSchema": {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {}
  },
  "outputSchema": {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "oneOf": [
      {
        "type": "object",
        "properties": {
          "status": {
            "type": "string",
            "const": "authenticated"
          },
          "account": {
            "type": "object",
            "properties": {
              "id": {
                "type": "string",
                "minLength": 1
              },
              "type": {
                "type": "string",
                "enum": [
                  "user",
                  "org",
                  "app"
                ]
              },
              "name": {
                "type": "string",
                "minLength": 1
              },
              "url": {
                "type": "string",
                "format": "uri"
              },
              "is_pro": {
                "type": "boolean"
              }
            },
            "required": [
              "id",
              "type",
              "name"
            ],
            "additionalProperties": false
          },
          "organizations": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "id": {
                  "type": "string",
                  "minLength": 1
                },
                "name": {
                  "type": "string",
                  "minLength": 1
                },
                "display_name": {
                  "type": "string",
                  "minLength": 1
                },
                "url": {
                  "type": "string",
                  "format": "uri"
                },
                "role": {
                  "type": "string",
                  "minLength": 1
                },
                "plan": {
                  "type": "string",
                  "minLength": 1
                },
                "security_restrictions": {
                  "type": "array",
                  "items": {
                    "type": "string",
                    "minLength": 1
                  }
                },
                "resource_groups": {
                  "type": "array",
                  "items": {
                    "type": "object",
                    "properties": {
                      "id": {
                        "type": "string",
                        "minLength": 1
                      },
                      "name": {
                        "type": "string",
                        "minLength": 1
                      },
                      "role": {
                        "type": "string",
                        "minLength": 1
                      }
                    },
                    "required": [
                      "id",
                      "name",
                      "role"
                    ],
                    "additionalProperties": false
                  }
                }
              },
              "required": [
                "id",
                "name",
                "display_name",
                "url"
              ],
              "additionalProperties": false
            }
          },
          "credential": {
            "oneOf": [
              {
                "type": "object",
                "properties": {
                  "type": {
                    "type": "string",
                    "const": "personal_access_token"
                  },
                  "role": {
                    "type": "string",
                    "enum": [
                      "read",
                      "write",
                      "fine_grained"
                    ]
                  },
                  "created_at": {
                    "type": "string",
                    "format": "date-time",
                    "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$"
                  },
                  "permissions": {
                    "type": "object",
                    "properties": {
                      "scoped": {
                        "type": "array",
                        "items": {
                          "type": "object",
                          "properties": {
                            "entity": {
                              "type": "object",
                              "properties": {
                                "id": {
                                  "type": "string",
                                  "minLength": 1
                                },
                                "type": {
                                  "type": "string",
                                  "enum": [
                                    "model",
                                    "dataset",
                                    "space",
                                    "bucket",
                                    "kernel",
                                    "collection",
                                    "org",
                                    "user",
                                    "resource_group",
                                    "oauth_app"
                                  ]
                                },
                                "name": {
                                  "type": "string",
                                  "minLength": 1
                                }
                              },
                              "required": [
                                "id",
                                "type"
                              ],
                              "additionalProperties": false
                            },
                            "permissions": {
                              "type": "array",
                              "items": {
                                "type": "string",
                                "minLength": 1
                              }
                            },
                            "restrictions": {
                              "type": "array",
                              "items": {
                                "type": "object",
                                "properties": {
                                  "resource_type": {
                                    "type": "string",
                                    "const": "inference_endpoint"
                                  },
                                  "patterns": {
                                    "type": "array",
                                    "items": {
                                      "type": "string",
                                      "minLength": 1
                                    }
                                  }
                                },
                                "required": [
                                  "resource_type",
                                  "patterns"
                                ],
                                "additionalProperties": false
                              }
                            }
                          },
                          "required": [
                            "entity",
                            "permissions"
                          ],
                          "additionalProperties": false
                        }
                      },
                      "global": {
                        "type": "array",
                        "items": {
                          "type": "string",
                          "minLength": 1
                        }
                      },
                      "can_read_gated_repos": {
                        "type": "boolean"
                      }
                    },
                    "required": [
                      "scoped"
                    ],
                    "additionalProperties": false
                  }
                },
                "required": [
                  "type",
                  "role"
                ],
                "additionalProperties": false
              },
              {
                "type": "object",
                "properties": {
                  "type": {
                    "type": "string",
                    "const": "oauth"
                  },
                  "expires_at": {
                    "type": "string",
                    "format": "date-time",
                    "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$"
                  },
                  "scopes": {
                    "type": "array",
                    "items": {
                      "type": "string",
                      "minLength": 1
                    }
                  }
                },
                "required": [
                  "type"
                ],
                "additionalProperties": false
              },
              {
                "type": "object",
                "properties": {
                  "type": {
                    "type": "string",
                    "const": "app_token"
                  },
                  "role": {
                    "type": "string",
                    "minLength": 1
                  },
                  "entities": {
                    "type": "array",
                    "items": {
                      "type": "object",
                      "properties": {
                        "type": {
                          "type": "string",
                          "enum": [
                            "model",
                            "dataset",
                            "space",
                            "bucket",
                            "kernel",
                            "org"
                          ]
                        },
                        "name": {
                          "type": "string",
                          "minLength": 1
                        }
                      },
                      "required": [
                        "name"
                      ],
                      "additionalProperties": false
                    }
                  }
                },
                "required": [
                  "type",
                  "entities"
                ],
                "additionalProperties": false
              },
              {
                "type": "object",
                "properties": {
                  "type": {
                    "type": "string",
                    "const": "other"
                  },
                  "expires_at": {
                    "type": "string",
                    "format": "date-time",
                    "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$"
                  }
                },
                "required": [
                  "type"
                ],
                "additionalProperties": false
              }
            ]
          }
        },
        "required": [
          "status",
          "account",
          "organizations",
          "credential"
        ],
        "additionalProperties": false
      },
      {
        "type": "object",
        "properties": {
          "status": {
            "type": "string",
            "const": "anonymous"
          },
          "account": {
            "type": "null"
          },
          "organizations": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "id": {
                  "type": "string",
                  "minLength": 1
                },
                "name": {
                  "type": "string",
                  "minLength": 1
                },
                "display_name": {
                  "type": "string",
                  "minLength": 1
                },
                "url": {
                  "type": "string",
                  "format": "uri"
                },
                "role": {
                  "type": "string",
                  "minLength": 1
                },
                "plan": {
                  "type": "string",
                  "minLength": 1
                },
                "security_restrictions": {
                  "type": "array",
                  "items": {
                    "type": "string",
                    "minLength": 1
                  }
                },
                "resource_groups": {
                  "type": "array",
                  "items": {
                    "type": "object",
                    "properties": {
                      "id": {
                        "type": "string",
                        "minLength": 1
                      },
                      "name": {
                        "type": "string",
                        "minLength": 1
                      },
                      "role": {
                        "type": "string",
                        "minLength": 1
                      }
                    },
                    "required": [
                      "id",
                      "name",
                      "role"
                    ],
                    "additionalProperties": false
                  }
                }
              },
              "required": [
                "id",
                "name",
                "display_name",
                "url"
              ],
              "additionalProperties": false
            }
          },
          "credential": {
            "type": "null"
          },
          "guidance": {
            "type": "string",
            "minLength": 1
          }
        },
        "required": [
          "status",
          "account",
          "organizations",
          "credential",
          "guidance"
        ],
        "additionalProperties": false
      },
      {
        "type": "object",
        "properties": {
          "status": {
            "type": "string",
            "const": "authentication_unverified"
          },
          "account": {
            "type": "null"
          },
          "organizations": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "id": {
                  "type": "string",
                  "minLength": 1
                },
                "name": {
                  "type": "string",
                  "minLength": 1
                },
                "display_name": {
                  "type": "string",
                  "minLength": 1
                },
                "url": {
                  "type": "string",
                  "format": "uri"
                },
                "role": {
                  "type": "string",
                  "minLength": 1
                },
                "plan": {
                  "type": "string",
                  "minLength": 1
                },
                "security_restrictions": {
                  "type": "array",
                  "items": {
                    "type": "string",
                    "minLength": 1
                  }
                },
                "resource_groups": {
                  "type": "array",
                  "items": {
                    "type": "object",
                    "properties": {
                      "id": {
                        "type": "string",
                        "minLength": 1
                      },
                      "name": {
                        "type": "string",
                        "minLength": 1
                      },
                      "role": {
                        "type": "string",
                        "minLength": 1
                      }
                    },
                    "required": [
                      "id",
                      "name",
                      "role"
                    ],
                    "additionalProperties": false
                  }
                }
              },
              "required": [
                "id",
                "name",
                "display_name",
                "url"
              ],
              "additionalProperties": false
            }
          },
          "credential": {
            "type": "null"
          },
          "guidance": {
            "type": "string",
            "minLength": 1
          }
        },
        "required": [
          "status",
          "account",
          "organizations",
          "credential",
          "guidance"
        ],
        "additionalProperties": false
      }
    ]
  }
}

hub_repo_search 6 params Search Hugging Face repositories with a shared query interface. You can target models, datasets, spaces, or ag…

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.

Input schema

Parameter	Type	Description & constraints
query	string	Search term. Leave blank and specify sort + limit to browse trending or recent repositories.
repo_types	array<enum(3)>	Repository types to search. Defaults to ["model", "dataset"]. space uses keyword search via /api/spaces. default: ["model","dataset"]
author	string	Organization or user namespace to filter by (e.g. 'google', 'meta-llama', 'huggingface').
filters	array<string>	Optional hub filter tags. Applied to each selected repo type (e.g. ["text-generation"], ["language:en"], ["mcp-server"]).
sort	enum(5)	Sort order (descending): trendingScore, downloads, likes, createdAt, lastModified one of: "trendingScore", "downloads", "likes", "createdAt", "lastModified"
limit	number	Maximum number of results to return per selected repo type min: 1 · max: 100 · default: 20

Raw schema JSON

hub_repo_search — raw

{
  "name": "hub_repo_search",
  "description": "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.",
  "inputSchema": {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "query": {
        "description": "Search term. Leave blank and specify sort + limit to browse trending or recent repositories.",
        "type": "string"
      },
      "repo_types": {
        "default": [
          "model",
          "dataset"
        ],
        "description": "Repository types to search. Defaults to [\"model\", \"dataset\"]. space uses keyword search via /api/spaces.",
        "minItems": 1,
        "maxItems": 3,
        "type": "array",
        "items": {
          "type": "string",
          "enum": [
            "model",
            "dataset",
            "space"
          ]
        }
      },
      "author": {
        "description": "Organization or user namespace to filter by (e.g. &#39;google&#39;, &#39;meta-llama&#39;, &#39;huggingface&#39;).",
        "type": "string"
      },
      "filters": {
        "description": "Optional hub filter tags. Applied to each selected repo type (e.g. [\"text-generation\"], [\"language:en\"], [\"mcp-server\"]).",
        "type": "array",
        "items": {
          "type": "string"
        }
      },
      "sort": {
        "description": "Sort order (descending): trendingScore, downloads, likes, createdAt, lastModified",
        "type": "string",
        "enum": [
          "trendingScore",
          "downloads",
          "likes",
          "createdAt",
          "lastModified"
        ]
      },
      "limit": {
        "default": 20,
        "description": "Maximum number of results to return per selected repo type",
        "type": "number",
        "minimum": 1,
        "maximum": 100
      }
    }
  }
}

hub_repo_details 7 params · 1 required Get details for one or more Hugging Face repos (model, dataset, or space). Auto-detects type unless specified.…

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.

Input schema

Parameter	Type	Description & constraints
repo_ids*	array<string>	Repo IDs for (models\|dataset/space) - usually in author/name format (e.g. openai/gpt-oss-120b)
repo_type	enum(3)	Specify lookup type; otherwise auto-detects one of: "model", "dataset", "space"
operations	array<enum(3)>	Details to return. Defaults to ["overview"]. For datasets, prefer ["overview", "dataset_structure"] first; then call ["dataset_preview"] with config and split.
config	string	Dataset Viewer config. Required for dataset_preview when the dataset has multiple config/split options. Discover via dataset_structure.
split	string	Dataset Viewer split. Required for dataset_preview when the dataset has multiple config/split options. Discover via dataset_structure.
offset	integer	Row offset for dataset_preview. Defaults to 0. min: 0 · max: 9007199254740991
limit	integer	Row count for dataset_preview. Defaults to 5 and is clamped to 1-100. min: -9007199254740991 · max: 9007199254740991

Raw schema JSON

hub_repo_details — raw

{
  "name": "hub_repo_details",
  "description": "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.",
  "inputSchema": {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "repo_ids": {
        "minItems": 1,
        "maxItems": 10,
        "type": "array",
        "items": {
          "type": "string",
          "minLength": 1
        },
        "description": "Repo IDs for (models|dataset/space) - usually in author/name format (e.g. openai/gpt-oss-120b)"
      },
      "repo_type": {
        "description": "Specify lookup type; otherwise auto-detects",
        "type": "string",
        "enum": [
          "model",
          "dataset",
          "space"
        ]
      },
      "operations": {
        "description": "Details to return. Defaults to [\"overview\"]. For datasets, prefer [\"overview\", \"dataset_structure\"] first; then call [\"dataset_preview\"] with config and split.",
        "type": "array",
        "items": {
          "type": "string",
          "enum": [
            "overview",
            "dataset_structure",
            "dataset_preview"
          ]
        }
      },
      "config": {
        "description": "Dataset Viewer config. Required for dataset_preview when the dataset has multiple config/split options. Discover via dataset_structure.",
        "type": "string"
      },
      "split": {
        "description": "Dataset Viewer split. Required for dataset_preview when the dataset has multiple config/split options. Discover via dataset_structure.",
        "type": "string"
      },
      "offset": {
        "description": "Row offset for dataset_preview. Defaults to 0.",
        "type": "integer",
        "minimum": 0,
        "maximum": 9007199254740991
      },
      "limit": {
        "description": "Row count for dataset_preview. Defaults to 5 and is clamped to 1-100.",
        "type": "integer",
        "minimum": -9007199254740991,
        "maximum": 9007199254740991
      }
    },
    "required": [
      "repo_ids"
    ]
  }
}

hf_fs 1 param · 1 required Use hf_fs for Hugging Face Hub filesystem operations. Call it with operations, an array of {cmd, args} items; …

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 discovery, ls for a known directory, find for recursive matching within a known scope, 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|datasets|spaces[/OWNER], hf://collections[/OWNER], hf://papers, and hf://docs[/...]. Paper and documentation search require QUERY. Repeat --tag only for search hf://spaces; --kind mcp selects MCP Spaces. Use ls hf://models/trending, hf://datasets/trending, hf://spaces/trending, or hf://papers/trending for trending listings. For a named paper.md or metadata.json, use cat directly. Use ls on a paper only to discover an unnamed related resource. 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.

Input schema

Parameter	Type	Description & constraints
operations*	array<object>	—
operations[].cmd*	enum(6)	Command to execute. one of: "ls", "cat", "attach", "stat", "find", "search"
operations[].args*	array<string>	Command arguments; each array item is one grammar token.

Output schema

Parameter	Type	Description & constraints
results*	array<object \| object>	—
truncated	boolean	—
truncation_reason	string	—

Raw schema JSON

hf_fs — raw

{
  "name": "hf_fs",
  "description": "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.\n\nUsage:\n  {\"operations\":[{\"cmd\":\"ls\",\"args\":[\"hf://models/org/repo\"]}]}\n\nGrammar; each string below is one args array item:\n  ls     URI [--recursive] [--glob GLOB] [--type TYPE] [--sort SORT] [--limit N]\n  cat    URI [--offset N] [--max-bytes N]\n  attach URI [--max-bytes N]\n  stat   URI\n  find   URI [--name GLOB] [--path GLOB] [--type TYPE] [--limit N]\n  search URI [QUERY] [--type TYPE] [--sort SORT] [--tag TAG] [--kind mcp] [--limit N]\n\nCOMMAND = ls|cat|attach|stat|find|search.\nTYPE = file|dir|repo|bucket|collection|paper|link.\nSORT = createdAt|downloads|likes|lastModified|likes30d|trendingScore|mainSize|id|trending|upvotes.\nURI is a canonical hf:// URI. QUERY and GLOB are each one string.\n\nUse search for discovery, ls for a known directory, find for recursive matching within a known scope, 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.\n\nSearch scopes: hf://models|datasets|spaces[/OWNER], hf://collections[/OWNER], hf://papers, and hf://docs[/...]. Paper and documentation search require QUERY. Repeat --tag only for search hf://spaces; --kind mcp selects MCP Spaces.\nUse ls hf://models/trending, hf://datasets/trending, hf://spaces/trending, or hf://papers/trending for trending listings.\nFor a named paper.md or metadata.json, use cat directly. Use ls on a paper only to discover an unnamed related resource.\nOmit --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.",
  "inputSchema": {
    "type": "object",
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "properties": {
      "operations": {
        "minItems": 1,
        "maxItems": 30,
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "cmd": {
              "type": "string",
              "enum": [
                "ls",
                "cat",
                "attach",
                "stat",
                "find",
                "search"
              ],
              "description": "Command to execute."
            },
            "args": {
              "type": "array",
              "items": {
                "type": "string"
              },
              "description": "Command arguments; each array item is one grammar token."
            }
          },
          "required": [
            "cmd",
            "args"
          ],
          "additionalProperties": false
        }
      }
    },
    "required": [
      "operations"
    ],
    "additionalProperties": false
  },
  "outputSchema": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "type": "object",
    "properties": {
      "results": {
        "minItems": 1,
        "maxItems": 30,
        "type": "array",
        "items": {
          "oneOf": [
            {
              "type": "object",
              "properties": {
                "index": {
                  "type": "integer",
                  "minimum": 0,
                  "maximum": 9007199254740991
                },
                "status": {
                  "type": "string",
                  "const": "success"
                },
                "result": {
                  "type": "object",
                  "properties": {
                    "uri": {
                      "type": "string"
                    },
                    "op": {
                      "type": "string",
                      "enum": [
                        "ls",
                        "cat",
                        "attach",
                        "stat",
                        "find",
                        "search"
                      ]
                    },
                    "entries": {
                      "type": "array",
                      "items": {
                        "type": "object",
                        "properties": {
                          "type": {
                            "type": "string",
                            "enum": [
                              "file",
                              "dir",
                              "repo",
                              "bucket",
                              "collection",
                              "paper",
                              "link"
                            ]
                          },
                          "path": {
                            "type": "string"
                          },
                          "uri": {
                            "type": "string"
                          },
                          "name": {
                            "type": "string"
                          },
                          "target_uri": {
                            "type": "string"
                          },
                          "repo_type": {
                            "type": "string",
                            "enum": [
                              "model",
                              "dataset",
                              "space",
                              "bucket"
                            ]
                          },
                          "size": {
                            "type": "number"
                          },
                          "total_files": {
                            "type": "number"
                          },
                          "lfs": {
                            "type": "boolean"
                          },
                          "private": {
                            "type": "boolean"
                          },
                          "gated": {
                            "anyOf": [
                              {
                                "type": "boolean",
                                "const": false
                              },
                              {
                                "type": "string",
                                "enum": [
                                  "auto",
                                  "manual"
                                ]
                              }
                            ]
                          },
                          "likes": {
                            "type": "number"
                          },
                          "downloads": {
                            "type": "number"
                          },
                          "task": {
                            "type": "string"
                          },
                          "library": {
                            "type": "string"
                          },
                          "tags": {
                            "type": "array",
                            "items": {
                              "type": "string"
                            }
                          },
                          "trending_score": {
                            "type": "number"
                          },
                          "sdk": {
                            "type": "string"
                          },
                          "title": {
                            "type": "string"
                          },
                          "category": {
                            "type": "string"
                          },
                          "semantic_relevance": {
                            "type": "number"
                          },
                          "anchor": {
                            "type": "string"
                          },
                          "description": {
                            "type": "string"
                          },
                          "upvotes": {
                            "type": "number"
                          },
                          "created_at": {
                            "type": "string"
                          },
                          "published_at": {
                            "type": "string"
                          },
                          "daily_papers_date": {
                            "type": "string"
                          },
                          "daily_papers_uri": {
                            "type": "string"
                          },
                          "url": {
                            "type": "string"
                          },
                          "arxiv_url": {
                            "type": "string"
                          },
                          "observed_at": {
                            "type": "string"
                          },
                          "updated_at": {
                            "type": "string"
                          },
                          "content_type": {
                            "type": "string",
                            "enum": [
                              "application/json",
                              "text/markdown"
                            ]
                          }
                        },
                        "required": [
                          "type",
                          "path"
                        ],
                        "additionalProperties": false
                      }
                    },
                    "path": {
                      "type": "string"
                    },
                    "content": {
                      "type": "string"
                    },
                    "content_type": {
                      "type": "string",
                      "enum": [
                        "application/json",
                        "text/markdown"
                      ]
                    },
                    "mime_type": {
                      "type": "string",
                      "enum": [
                        "image/jpeg",
                        "image/png",
                        "image/webp"
                      ]
                    },
                    "section": {
                      "type": "string"
                    },
                    "bytes": {
                      "type": "number"
                    },
                    "exists": {
                      "type": "boolean"
                    },
                    "type": {
                      "type": "string",
                      "enum": [
                        "namespace",
                        "repo",
                        "dir",
                        "file",
                        "collection",
                        "paper",
                        "link",
                        "missing"
                      ]
                    },
                    "namespace": {
                      "type": "string"
                    },
                    "size": {
                      "type": "number"
                    },
                    "lfs": {
                      "type": "boolean"
                    },
                    "target_uri": {
                      "type": "string"
                    },
                    "published_at": {
                      "type": "string"
                    },
                    "daily_papers_date": {
                      "type": "string"
                    },
                    "daily_papers_uri": {
                      "type": "string"
                    },
                    "url": {
                      "type": "string"
                    },
                    "arxiv_url": {
                      "type": "string"
                    },
                    "truncated": {
                      "type": "boolean"
                    },
                    "truncation_reason": {
                      "type": "string",
                      "enum": [
                        "entry_limit",
                        "max_bytes",
                        "limit",
                        "provider_limit"
                      ]
                    },
                    "truncation_message": {
                      "type": "string"
                    },
                    "next_offset": {
                      "type": "number"
                    },
                    "warnings": {
                      "type": "array",
                      "items": {
                        "type": "string"
                      }
                    }
                  },
                  "required": [
                    "uri",
                    "op"
                  ],
                  "additionalProperties": false,
                  "allOf": [
                    {
                      "if": {
                        "properties": {
                          "op": {
                            "const": "attach"
                          }
                        },
                        "required": [
                          "op"
                        ]
                      },
                      "then": {
                        "properties": {
                          "path": {
                            "type": "string"
                          },
                          "mime_type": {
                            "type": "string",
                            "enum": [
                              "image/jpeg",
                              "image/png",
                              "image/webp"
                            ]
                          },
                          "bytes": {
                            "type": "integer",
                            "minimum": 0,
                            "maximum": 8388608
                          }
                        },
                        "required": [
                          "path",
                          "mime_type",
                          "bytes"
                        ]
                      }
                    }
                  ]
                },
                "output_truncated": {
                  "type": "boolean"
                }
              },
              "required": [
                "index",
                "status",
                "result"
              ],
              "additionalProperties": false
            },
            {
              "type": "object",
              "properties": {
                "index": {
                  "type": "integer",
                  "minimum": 0,
                  "maximum": 9007199254740991
                },
                "status": {
                  "type": "string",
                  "const": "error"
                },
                "error": {
                  "type": "object",
                  "properties": {
                    "code": {
                      "type": "string",
                      "enum": [
                        "HF_FS_INVALID_ARGUMENT",
                        "HF_FS_NOT_FOUND",
                        "HF_FS_NOT_A_DIRECTORY",
                        "HF_FS_NOT_A_FILE",
                        "HF_FS_UNSUPPORTED_OPERATION",
                        "HF_FS_ACCESS_DENIED",
                        "HF_FS_TEXT_ONLY",
                        "HF_FS_IMAGE_ONLY",
                        "HF_FS_UNSUPPORTED_MEDIA",
                        "HF_FS_IMAGE_TOO_LARGE",
                        "HF_FS_ATTACHMENT_BUDGET_EXCEEDED",
                        "HF_FS_IMAGE_CONTENT_DISABLED",
                        "HF_FS_ATTACHMENT_INTEGRITY"
                      ]
                    },
                    "message": {
                      "type": "string"
                    },
                    "recovery": {
                      "type": "string"
                    },
                    "retryable": {
                      "type": "boolean",
                      "const": false
                    },
                    "suggestedOperation": {
                      "type": "string",
                      "enum": [
                        "ls",
                        "cat",
                        "attach",
                        "stat",
                        "search"
                      ]
                    }
                  },
                  "required": [
                    "code",
                    "message",
                    "recovery",
                    "retryable"
                  ],
                  "additionalProperties": false
                }
              },
              "required": [
                "index",
                "status",
                "error"
              ],
              "additionalProperties": false
            }
          ]
        }
      },
      "truncated": {
        "type": "boolean"
      },
      "truncation_reason": {
        "type": "string",
        "const": "output_budget"
      }
    },
    "required": [
      "results"
    ],
    "additionalProperties": false
  }
}

Resources 155

URI	Name	MIME type	Description
skill://hf-cli/SKILL.md	hf-cli	`text/markdown`	Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastructure; managing Hugging Face repos; discussions and pull requests; browsing models, datasets and spaces; reading, searching, or browsing academic papers; managing collections; querying datasets; configuring spaces; setting up webhooks; or deploying and managing HF Inference Endpoints. Make sure to use this skill whenever the user mentions 'hf', 'huggingface', 'Hugging Face', 'huggingface-cli', or 'hugging face cli', or wants to do anything related to the Hugging Face ecosystem and to AI and ML in general. Also use for cloud storage needs like training checkpoints, data pipelines, or agent traces. Use even if the user doesn't explicitly ask for a CLI command. Replaces the deprecated `huggingface-cli`.
skill://hf-cloud-aws-context-discovery/SKILL.md	hf-cloud-aws-context-discovery	`text/markdown`	Discover the user's local AWS context (active profile, region, account ID, caller identity) at the start of any AWS task. Use this skill before any other AWS work — deploying to SageMaker, creating resources, calling AWS APIs, or anything that touches an AWS account. Use it especially when the user has not specified a region or profile explicitly, when they say things like "use my AWS account", "deploy to AWS", "use my profile", or when about to make any AWS CLI or SDK call. Never guess the region or account ID — always use this skill to read it from the local configuration first.
skill://hf-cloud-python-env-setup/SKILL.md	hf-cloud-python-env-setup	`text/markdown`	Set up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMaker deployment, training job, or any AWS automation — including when about to run `pip install`, when about to invoke `boto3`, when creating or activating a virtualenv, or when the user asks to "set up the environment". Never use system Python and never `pip install` into it. Always isolate. This skill prevents the most common failure modes: wrong Python version, dependency conflicts, and stale SDKs.
skill://hf-cloud-python-env-setup/requirements.txt	requirements.txt	`text/plain`	—
skill://hf-cloud-python-env-setup/scripts/check_versions.py	check_versions.py	`text/x-python`	—
skill://hf-cloud-python-env-setup/scripts/setup_env.py	setup_env.py	`text/x-python`	—
skill://hf-cloud-sagemaker-deployment-planner/SKILL.md	hf-cloud-sagemaker-deployment-planner	`text/markdown`	Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on SageMaker or AWS — including phrases like "deploy a model", "host this LLM on AWS", "serve this embedding model", "deploy a reranker", "deploy a text-to-image / diffusion model", "host this for async inference", "create an endpoint", "serve my fine-tuned model", or any request that involves making a model available for inference on AWS. Use this even when the user is vague (e.g. "I just want to get this running on AWS, you figure it out"). Works for text-generation LLMs, embedding models, rerankers, classifiers, text-to-image / diffusion models — picks the right serving stack and chooses between real-time and async inference. This is the entry-point skill for SageMaker deployment work — it asks clarifying questions, picks a deployment pathway, and coordinates the other deployment skills.
skill://hf-cloud-sagemaker-iam-preflight/SKILL.md	hf-cloud-sagemaker-iam-preflight	`text/markdown`	Ensure a usable SageMaker execution role exists before deploying or training. Use this skill whenever about to create a SageMaker endpoint, model, training job, or any resource that requires an execution role. Use it especially when the user has not provided a role ARN explicitly, when scripts are about to call `iam:CreateRole`, or when an AccessDenied error mentions an IAM action. Never blindly call `iam:CreateRole` — always check for existing roles first. This skill prevents the most common SageMaker deployment failure: trying to create IAM resources from an SSO principal that has no IAM write permissions.
skill://hf-cloud-sagemaker-iam-preflight/references/minimum-permissions.json	minimum-permissions.json	`application/json`	—
skill://hf-cloud-sagemaker-iam-preflight/references/trust-policy.json	trust-policy.json	`application/json`	—
skill://hf-cloud-sagemaker-iam-preflight/scripts/check_role.py	check_role.py	`text/x-python`	—
skill://hf-cloud-sagemaker-iam-preflight/scripts/create_role.py	create_role.py	`text/x-python`	—
skill://hf-cloud-sagemaker-production-defaults/SKILL.md	hf-cloud-sagemaker-production-defaults	`text/markdown`	Create a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a SageMaker endpoint, write deployment code that calls `create_endpoint`, or finalize a deployment after the image URI and IAM role are known. Provides deploy.py for real-time endpoints, deploy_ic.py for real-time endpoints that scale to zero instances via inference components, and deploy_async.py for async endpoints (also scale-to-zero). This is the last step in the SageMaker deployment workflow. Never generate a bare `create_endpoint` call without these defaults — endpoints without autoscaling or alarms are demos, not deployments.
skill://hf-cloud-sagemaker-production-defaults/references/deployment-template.md	deployment-template.md	`text/markdown`	—
skill://hf-cloud-sagemaker-production-defaults/scripts/_common.py	_common.py	`text/x-python`	—
skill://hf-cloud-sagemaker-production-defaults/scripts/deploy.py	deploy.py	`text/x-python`	—
skill://hf-cloud-sagemaker-production-defaults/scripts/deploy_async.py	deploy_async.py	`text/x-python`	—
skill://hf-cloud-sagemaker-production-defaults/scripts/deploy_ic.py	deploy_ic.py	`text/x-python`	—
skill://hf-cloud-sagemaker-production-defaults/scripts/invoke_endpoint.py	invoke_endpoint.py	`text/x-python`	—
skill://hf-cloud-sagemaker-production-defaults/scripts/teardown.py	teardown.py	`text/x-python`	—
skill://hf-cloud-serving-image-selection/SKILL.md	hf-cloud-serving-image-selection	`text/markdown`	Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.
skill://hf-cloud-serving-image-selection/references/model-to-image.md	model-to-image.md	`text/markdown`	—
skill://hf-cloud-serving-image-selection/scripts/mirror_image.py	mirror_image.py	`text/x-python`	—
skill://hf-mem/SKILL.md	hf-mem	`text/markdown`	Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub
skill://huggingface-best/SKILL.md	huggingface-best	`text/markdown`	Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores. Triggers on: "best model for X", "what model should I use for", "top models for [task]", "which model runs on my laptop/machine/device", "recommend a model for", "what LLM should I use for", "compare models for", "what's state of the art for", or any question about choosing an AI model for a specific use case. Always use this skill when the user wants model recommendations or comparisons, even if they don't explicitly mention HuggingFace or benchmarks.
skill://huggingface-community-evals/SKILL.md	huggingface-community-evals	`text/markdown`	Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.
skill://huggingface-community-evals/examples/.env.example	.env.example	`application/octet-stream`	—
skill://huggingface-community-evals/examples/USAGE_EXAMPLES.md	USAGE_EXAMPLES.md	`text/markdown`	—
skill://huggingface-community-evals/scripts/inspect_eval_uv.py	inspect_eval_uv.py	`text/x-python`	—
skill://huggingface-community-evals/scripts/inspect_vllm_uv.py	inspect_vllm_uv.py	`text/x-python`	—
skill://huggingface-community-evals/scripts/lighteval_vllm_uv.py	lighteval_vllm_uv.py	`text/x-python`	—
skill://huggingface-datasets/SKILL.md	huggingface-datasets	`text/markdown`	Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.
skill://huggingface-gradio/SKILL.md	huggingface-gradio	`text/markdown`	Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.
skill://huggingface-gradio/examples.md	examples.md	`text/markdown`	—
skill://huggingface-llm-trainer/SKILL.md	huggingface-llm-trainer	`text/markdown`	Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
skill://huggingface-llm-trainer/references/gguf_conversion.md	gguf_conversion.md	`text/markdown`	—
skill://huggingface-llm-trainer/references/hardware_guide.md	hardware_guide.md	`text/markdown`	—
skill://huggingface-llm-trainer/references/hub_saving.md	hub_saving.md	`text/markdown`	—
skill://huggingface-llm-trainer/references/local_training_macos.md	local_training_macos.md	`text/markdown`	—
skill://huggingface-llm-trainer/references/reliability_principles.md	reliability_principles.md	`text/markdown`	—
skill://huggingface-llm-trainer/references/trackio_guide.md	trackio_guide.md	`text/markdown`	—
skill://huggingface-llm-trainer/references/training_methods.md	training_methods.md	`text/markdown`	—
skill://huggingface-llm-trainer/references/training_patterns.md	training_patterns.md	`text/markdown`	—
skill://huggingface-llm-trainer/references/troubleshooting.md	troubleshooting.md	`text/markdown`	—
skill://huggingface-llm-trainer/references/unsloth.md	unsloth.md	`text/markdown`	—
skill://huggingface-llm-trainer/scripts/convert_to_gguf.py	convert_to_gguf.py	`text/x-python`	—
skill://huggingface-llm-trainer/scripts/dataset_inspector.py	dataset_inspector.py	`text/x-python`	—
skill://huggingface-llm-trainer/scripts/estimate_cost.py	estimate_cost.py	`text/x-python`	—
skill://huggingface-llm-trainer/scripts/hf_benchmarks.py	hf_benchmarks.py	`text/x-python`	—
skill://huggingface-llm-trainer/scripts/train_dpo_example.py	train_dpo_example.py	`text/x-python`	—
skill://huggingface-llm-trainer/scripts/train_grpo_example.py	train_grpo_example.py	`text/x-python`	—
skill://huggingface-llm-trainer/scripts/train_sft_example.py	train_sft_example.py	`text/x-python`	—
skill://huggingface-llm-trainer/scripts/unsloth_sft_example.py	unsloth_sft_example.py	`text/x-python`	—
skill://huggingface-local-models/SKILL.md	huggingface-local-models	`text/markdown`	Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.
skill://huggingface-local-models/references/hardware.md	hardware.md	`text/markdown`	—
skill://huggingface-local-models/references/hub-discovery.md	hub-discovery.md	`text/markdown`	—
skill://huggingface-local-models/references/quantization.md	quantization.md	`text/markdown`	—
skill://huggingface-lora-space-builder/SKILL.md	huggingface-lora-space-builder	`text/markdown`	Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan, FLUX, SDXL, or other diffusion base models. Also triggers when someone describes a LoRA they trained or hosts on the Hub and wants to share it. Covers picking the right base pipeline and `diffusers` inference recipe, designing a UI tailored to the LoRA's task and inputs (Union/multi-task control, edit, video, image, etc.), respecting model-card recommendations (trigger words, steps, guidance, LoRA scale, example inputs), and shipping to ZeroGPU hardware as a private Space by default.
skill://huggingface-lora-space-builder/references/adapting-to-the-lora.md	adapting-to-the-lora.md	`text/markdown`	—
skill://huggingface-lora-space-builder/references/base-models/krea-2.md	krea-2.md	`text/markdown`	—
skill://huggingface-lora-space-builder/references/base-models/ltx.md	ltx.md	`text/markdown`	—
skill://huggingface-lora-space-builder/references/base-models/qwen-image.md	qwen-image.md	`text/markdown`	—
skill://huggingface-lora-space-builder/references/creative-mode.md	creative-mode.md	`text/markdown`	—
skill://huggingface-lora-space-builder/references/tasks.md	tasks.md	`text/markdown`	—
skill://huggingface-lora-space-builder/references/zerogpu-and-publishing.md	zerogpu-and-publishing.md	`text/markdown`	—
skill://huggingface-paper-publisher/SKILL.md	huggingface-paper-publisher	`text/markdown`	Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.
skill://huggingface-paper-publisher/examples/example_usage.md	example_usage.md	`text/markdown`	—
skill://huggingface-paper-publisher/references/quick_reference.md	quick_reference.md	`text/markdown`	—
skill://huggingface-paper-publisher/scripts/paper_manager.py	paper_manager.py	`text/x-python`	—
skill://huggingface-paper-publisher/templates/arxiv.md	arxiv.md	`text/markdown`	—
skill://huggingface-paper-publisher/templates/ml-report.md	ml-report.md	`text/markdown`	—
skill://huggingface-paper-publisher/templates/modern.md	modern.md	`text/markdown`	—
skill://huggingface-paper-publisher/templates/standard.md	standard.md	`text/markdown`	—
skill://huggingface-papers/SKILL.md	huggingface-papers	`text/markdown`	Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper.
skill://huggingface-spaces/README.md	README.md	`text/markdown`	—
skill://huggingface-spaces/SKILL.md	huggingface-spaces	`text/markdown`	Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on Hugging Face, port code onto ZeroGPU, fix a Space that won't build or run, or otherwise work with `hf spaces …`, `@spaces.GPU`, Space README frontmatter, or the `spaces` Python package.
skill://huggingface-spaces/references/3d-cuda-extensions.md	3d-cuda-extensions.md	`text/markdown`	—
skill://huggingface-spaces/references/3d-generation.md	3d-generation.md	`text/markdown`	—
skill://huggingface-spaces/references/3d-gsplat.md	3d-gsplat.md	`text/markdown`	—
skill://huggingface-spaces/references/3d-models.md	3d-models.md	`text/markdown`	—
skill://huggingface-spaces/references/3d-outputs.md	3d-outputs.md	`text/markdown`	—
skill://huggingface-spaces/references/buckets.md	buckets.md	`text/markdown`	—
skill://huggingface-spaces/references/debugging.md	debugging.md	`text/markdown`	—
skill://huggingface-spaces/references/gradio.md	gradio.md	`text/markdown`	—
skill://huggingface-spaces/references/grants.md	grants.md	`text/markdown`	—
skill://huggingface-spaces/references/inference-providers.md	inference-providers.md	`text/markdown`	—
skill://huggingface-spaces/references/known-errors.md	known-errors.md	`text/markdown`	—
skill://huggingface-spaces/references/requirements.md	requirements.md	`text/markdown`	—
skill://huggingface-spaces/references/zerogpu.md	zerogpu.md	`text/markdown`	—
skill://huggingface-tool-builder/SKILL.md	huggingface-tool-builder	`text/markdown`	Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusable script to fetch, enrich or process data.
skill://huggingface-tool-builder/references/baseline_hf_api.py	baseline_hf_api.py	`text/x-python`	—
skill://huggingface-tool-builder/references/baseline_hf_api.sh	baseline_hf_api.sh	`application/x-sh`	—
skill://huggingface-tool-builder/references/baseline_hf_api.tsx	baseline_hf_api.tsx	`text/x-typescript`	—
skill://huggingface-tool-builder/references/find_models_by_paper.sh	find_models_by_paper.sh	`application/x-sh`	—
skill://huggingface-tool-builder/references/hf_enrich_models.sh	hf_enrich_models.sh	`application/x-sh`	—
skill://huggingface-tool-builder/references/hf_model_card_frontmatter.sh	hf_model_card_frontmatter.sh	`application/x-sh`	—
skill://huggingface-tool-builder/references/hf_model_papers_auth.sh	hf_model_papers_auth.sh	`application/x-sh`	—
skill://huggingface-trackio/SKILL.md	huggingface-trackio	`text/markdown`	Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, alerts with webhooks, HF Space syncing, and JSON output for automation.
skill://huggingface-trackio/references/alerts.md	alerts.md	`text/markdown`	—
skill://huggingface-trackio/references/logging_metrics.md	logging_metrics.md	`text/markdown`	—
skill://huggingface-trackio/references/retrieving_metrics.md	retrieving_metrics.md	`text/markdown`	—
skill://huggingface-vision-trainer/SKILL.md	huggingface-vision-trainer	`text/markdown`	Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
skill://huggingface-vision-trainer/references/finetune_sam2_trainer.md	finetune_sam2_trainer.md	`text/markdown`	—
skill://huggingface-vision-trainer/references/hub_saving.md	hub_saving.md	`text/markdown`	—
skill://huggingface-vision-trainer/references/image_classification_training_notebook.md	image_classification_training_notebook.md	`text/markdown`	—
skill://huggingface-vision-trainer/references/object_detection_training_notebook.md	object_detection_training_notebook.md	`text/markdown`	—
skill://huggingface-vision-trainer/references/reliability_principles.md	reliability_principles.md	`text/markdown`	—
skill://huggingface-vision-trainer/references/timm_trainer.md	timm_trainer.md	`text/markdown`	—
skill://huggingface-vision-trainer/scripts/dataset_inspector.py	dataset_inspector.py	`text/x-python`	—
skill://huggingface-vision-trainer/scripts/estimate_cost.py	estimate_cost.py	`text/x-python`	—
skill://huggingface-vision-trainer/scripts/image_classification_training.py	image_classification_training.py	`text/x-python`	—
skill://huggingface-vision-trainer/scripts/object_detection_training.py	object_detection_training.py	`text/x-python`	—
skill://huggingface-vision-trainer/scripts/sam_segmentation_training.py	sam_segmentation_training.py	`text/x-python`	—
skill://huggingface-zerogpu/SKILL.md	huggingface-zerogpu	`text/markdown`	AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU. Use when writing or reviewing code that uses `@spaces.GPU`, configuring `python_version` or `requirements.txt` for a ZeroGPU Space, or handling ZeroGPU-specific code constraints — pickle-based process isolation, `gr.State` semantics across the worker boundary, no `torch.compile` (use AoTI instead), CUDA wheel-only builds (no `nvcc` at build or runtime), large vs xlarge sizing, and dynamic duration callables. Make sure to use this skill whenever the user mentions ZeroGPU, `@spaces.GPU`, or the `spaces` Python package, or hits ZeroGPU-specific code errors like `PicklingError` across the worker boundary, `illegal duration`, or `flash-attn` wheel-build failures — even when the user does not explicitly ask for ZeroGPU coding guidance. Trigger on `import spaces` or `@spaces.GPU` in code.
skill://huggingface-zerogpu/references/concurrency.md	concurrency.md	`text/markdown`	—
skill://huggingface-zerogpu/references/cuda-and-deps.md	cuda-and-deps.md	`text/markdown`	—
skill://huggingface-zerogpu/references/how-quota-works.md	how-quota-works.md	`text/markdown`	—
skill://huggingface-zerogpu/references/how-zerogpu-works.md	how-zerogpu-works.md	`text/markdown`	—
skill://train-sentence-transformers/SKILL.md	train-sentence-transformers	`text/markdown`	Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker; pair scoring for two-stage retrieval / pair classification), and `SparseEncoder` (SPLADE, sparse embedding model; for learned-sparse retrieval). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.
skill://train-sentence-transformers/references/base_model_selection.md	base_model_selection.md	`text/markdown`	—
skill://train-sentence-transformers/references/dataset_formats.md	dataset_formats.md	`text/markdown`	—
skill://train-sentence-transformers/references/evaluators_cross_encoder.md	evaluators_cross_encoder.md	`text/markdown`	—
skill://train-sentence-transformers/references/evaluators_sentence_transformer.md	evaluators_sentence_transformer.md	`text/markdown`	—
skill://train-sentence-transformers/references/evaluators_sparse_encoder.md	evaluators_sparse_encoder.md	`text/markdown`	—
skill://train-sentence-transformers/references/hardware_guide.md	hardware_guide.md	`text/markdown`	—
skill://train-sentence-transformers/references/hf_jobs_execution.md	hf_jobs_execution.md	`text/markdown`	—
skill://train-sentence-transformers/references/losses_cross_encoder.md	losses_cross_encoder.md	`text/markdown`	—
skill://train-sentence-transformers/references/losses_sentence_transformer.md	losses_sentence_transformer.md	`text/markdown`	—
skill://train-sentence-transformers/references/losses_sparse_encoder.md	losses_sparse_encoder.md	`text/markdown`	—
skill://train-sentence-transformers/references/model_architectures.md	model_architectures.md	`text/markdown`	—
skill://train-sentence-transformers/references/prompts_and_instructions.md	prompts_and_instructions.md	`text/markdown`	—
skill://train-sentence-transformers/references/training_args.md	training_args.md	`text/markdown`	—
skill://train-sentence-transformers/references/troubleshooting.md	troubleshooting.md	`text/markdown`	—
skill://train-sentence-transformers/scripts/mine_hard_negatives.py	mine_hard_negatives.py	`text/x-python`	—
skill://train-sentence-transformers/scripts/train_cross_encoder_distillation_example.py	train_cross_encoder_distillation_example.py	`text/x-python`	—
skill://train-sentence-transformers/scripts/train_cross_encoder_example.py	train_cross_encoder_example.py	`text/x-python`	—
skill://train-sentence-transformers/scripts/train_cross_encoder_listwise_example.py	train_cross_encoder_listwise_example.py	`text/x-python`	—
skill://train-sentence-transformers/scripts/train_sentence_transformer_distillation_example.py	train_sentence_transformer_distillation_example.py	`text/x-python`	—
skill://train-sentence-transformers/scripts/train_sentence_transformer_example.py	train_sentence_transformer_example.py	`text/x-python`	—
skill://train-sentence-transformers/scripts/train_sentence_transformer_make_multilingual_example.py	train_sentence_transformer_make_multilingual_example.py	`text/x-python`	—
skill://train-sentence-transformers/scripts/train_sentence_transformer_matryoshka_example.py	train_sentence_transformer_matryoshka_example.py	`text/x-python`	—
skill://train-sentence-transformers/scripts/train_sentence_transformer_multi_dataset_example.py	train_sentence_transformer_multi_dataset_example.py	`text/x-python`	—
skill://train-sentence-transformers/scripts/train_sentence_transformer_static_embedding_example.py	train_sentence_transformer_static_embedding_example.py	`text/x-python`	—
skill://train-sentence-transformers/scripts/train_sentence_transformer_with_lora_example.py	train_sentence_transformer_with_lora_example.py	`text/x-python`	—
skill://train-sentence-transformers/scripts/train_sparse_encoder_distillation_example.py	train_sparse_encoder_distillation_example.py	`text/x-python`	—
skill://train-sentence-transformers/scripts/train_sparse_encoder_example.py	train_sparse_encoder_example.py	`text/x-python`	—
skill://transformers-js/SKILL.md	transformers-js	`text/markdown`	Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in browsers and server-side runtimes (Node.js, Bun, Deno) with WebGPU/WASM using pre-trained models from Hugging Face Hub.
skill://transformers-js/references/CACHE.md	CACHE.md	`text/markdown`	—
skill://transformers-js/references/CONFIGURATION.md	CONFIGURATION.md	`text/markdown`	—
skill://transformers-js/references/EXAMPLES.md	EXAMPLES.md	`text/markdown`	—
skill://transformers-js/references/MODEL_ARCHITECTURES.md	MODEL_ARCHITECTURES.md	`text/markdown`	—
skill://transformers-js/references/MODEL_REGISTRY.md	MODEL_REGISTRY.md	`text/markdown`	—
skill://transformers-js/references/PIPELINE_OPTIONS.md	PIPELINE_OPTIONS.md	`text/markdown`	—
skill://transformers-js/references/TEXT_GENERATION.md	TEXT_GENERATION.md	`text/markdown`	—
skill://trl-training/SKILL.md	trl-training	`text/markdown`	Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.

Prompts 0

No prompts advertised.

Inventory recorded Aug 21, 2026 — 9:41 AM as rev 4. Listing calls only — tools are never invoked.

Canonical contract hash

contract hash — rev 4

sha256:5575083c8b77e5270879bcf164d83c037c35b0a0fd44d0c1dd8f36c04b466243

Computed centrally from the normalized capability inventory (normalizer v1). Scanners submit raw observations; the control plane normalizes and hashes, so every scanner agrees on the same value.

Revisions 4

Rev	Observed	Hash
rev 4	Aug 21, 2026 — 9:41 AM (27 d ago)
rev 3	Aug 14, 2026 — 1:15 PM (34 d ago)
rev 2	Aug 7, 2026 — 2:41 PM (41 d ago)
rev 1 baseline	Aug 6, 2026 — 5:10 AM (43 d ago)

Contract changes 3

Breaking 27 breaking, 3 potentially breaking, 1 non-breaking changes. Required parameter operations was added at hf_fs.inputSchema. rev 3 → 4 · 27 d ago

Potentially breaking 1 potentially breaking, 3 non-breaking changes. Schema composition (allOf) at hf_fs.outputSchema changed. rev 2 → 3 · 34 d ago

Non-breaking 1 non-breaking change. Tool hf_whoami now declares an output schema. rev 1 → 2 · 41 d ago

Full snapshots are stored only when the canonical hash changes — unchanged observations update freshness without duplicating the contract.

Recent observations latest 30

Observed	Result	Latency
Sep 17, 2026 — 6:50 PM (1 h ago)	Reachable	43 ms
Sep 17, 2026 — 4:45 PM (3 h ago)	Reachable	46 ms
Sep 17, 2026 — 2:40 PM (6 h ago)	Reachable	52 ms
Sep 17, 2026 — 12:35 PM (8 h ago)	Reachable	47 ms
Sep 17, 2026 — 10:35 AM (10 h ago)	Reachable	34 ms
Sep 17, 2026 — 8:30 AM (12 h ago)	Reachable	36 ms
Sep 17, 2026 — 6:25 AM (14 h ago)	Reachable	36 ms
Sep 17, 2026 — 4:20 AM (16 h ago)	Reachable	44 ms
Sep 17, 2026 — 2:15 AM (18 h ago)	Reachable	66 ms
Sep 17, 2026 — 12:15 AM (20 h ago)	Reachable	42 ms
Sep 16, 2026 — 10:10 PM (22 h ago)	Reachable	35 ms
Sep 16, 2026 — 8:05 PM (1 d ago)	Reachable	74 ms
Sep 16, 2026 — 6:01 PM (1 d ago)	Reachable	67 ms
Sep 16, 2026 — 4:00 PM (1 d ago)	Reachable	46 ms
Sep 16, 2026 — 1:55 PM (1 d ago)	Reachable	207 ms
Sep 16, 2026 — 11:50 AM (1 d ago)	Reachable	1111 ms
Sep 16, 2026 — 9:50 AM (1 d ago)	Reachable	36 ms
Sep 16, 2026 — 7:45 AM (2 d ago)	Reachable	40 ms
Sep 16, 2026 — 5:40 AM (2 d ago)	Reachable	37 ms
Sep 16, 2026 — 3:35 AM (2 d ago)	Reachable	53 ms
Sep 16, 2026 — 1:30 AM (2 d ago)	Reachable	64 ms
Sep 15, 2026 — 11:25 PM (2 d ago)	Reachable	54 ms
Sep 15, 2026 — 9:25 PM (2 d ago)	Reachable	39 ms
Sep 15, 2026 — 7:20 PM (2 d ago)	Reachable	5911 ms
Sep 15, 2026 — 5:15 PM (2 d ago)	Reachable	139 ms
Sep 15, 2026 — 3:15 PM (2 d ago)	Reachable	78 ms
Sep 15, 2026 — 1:15 PM (2 d ago)	Reachable	57 ms
Sep 15, 2026 — 11:10 AM (2 d ago)	Reachable	36 ms
Sep 15, 2026 — 9:10 AM (2 d ago)	Reachable	31 ms
Sep 15, 2026 — 7:10 AM (3 d ago)	Reachable	940 ms

Latest check — evidence & validation Sep 17, 2026 — 6:50 PM

Reachable MCP Tools Edge Scanner ScheduledHTTP 20043 msStreamable HTTP2025-06-18

response headers (as observed)

{
  "server": "cloudflare",
  "content-type": "application/json",
  "mcp-session-id": "9afc5ce0-4c31-49ae-a998-f639580aecba"
}

serverInfo — from initialize

{
  "name": "huggingface.co/mcp",
  "version": "0.4.20",
  "title": "Hugging Face"
}

Server name	`huggingface.co/mcp`
Server version	`0.4.20`
Transport	Streamable HTTP
Protocol version	`2025-06-18`
First observed	Aug 6, 2026
Last observed	1 h ago
Last successful	1 h ago
Origin	Registry seed

Hugging Face MCP · Hugging Face

Availability — last 30 days

Advertised capabilities

Tools 4

Input schema

Output schema

Input schema

Input schema

Input schema

Output schema

Resources 155

Prompts 0

Canonical contract hash

Revisions 4

Contract changes 3

Recent observations latest 30

Publisher supplied

Independently observed

Name	Hugging Face MCP
Vendor	Hugging Face
Category	developer-tools
Docs	https://huggingface.co/docs/hub/en/agents-mcp
Repository	—
Auth expected	API key expected