Can I use Hugging Face as a CLI?

Yes. KosmoKrator exposes a Hugging Face CLI through kosmo integrations:call and the provider shortcut command. Commands can return JSON for scripts, CI, and coding agents.

Can I expose Hugging Face through MCP?

Yes. The KosmoKrator MCP gateway can expose selected Hugging Face tools to clients such as Claude Code, Cursor, Codex, and other MCP-compatible tools.

Where are Hugging Face credentials stored?

Hugging Face credentials are configured in KosmoKrator's local integration settings and reused by CLI, Lua, and MCP gateway surfaces.

Can I deny write access for Hugging Face MCP tools?

Yes. Start the gateway with --write=deny for read-only clients, or use ask/allow only for trusted workspaces.

Hugging Face CLI for AI Agents

Use the Hugging Face CLI from KosmoKrator to call Hugging Face tools headlessly, return JSON, inspect schemas, and automate workflows from coding agents, scripts, and CI.

6 functions 5 read 1 write Bearer token auth

Submit Hugging Face feedback View package source

Hugging Face CLI Setup

Hugging Face can be configured headlessly with `kosmokrator integrations:configure hugging-face`.

# Install KosmoKrator first if it is not available on PATH.
curl -fsSL https://raw.githubusercontent.com/OpenCompanyApp/kosmokrator/main/install.sh | bash

# Configure and verify this integration.
kosmokrator integrations:configure hugging-face --set access_token="$HUGGING_FACE_ACCESS_TOKEN" --enable --read allow --write ask --json
kosmokrator integrations:doctor hugging-face --json
kosmokrator integrations:status --json

Credentials

Authentication type: Bearer token bearer_token. Configure credentials once, then use the same stored profile from scripts, coding CLIs, Lua code mode, and the MCP gateway.

Key	Env var	Type	Required	Label
`access_token`	`HUGGING_FACE_ACCESS_TOKEN`	Secret `secret`	yes	Access Token
`url`	`HUGGING_FACE_URL`	URL `url`	no	API Base URL

Call Hugging Face Headlessly

Use the generic call form when another coding CLI or script needs a stable universal interface.

kosmo integrations:call hugging-face.huggingface_list_models '{
  "search": "example_search",
  "author": "example_author",
  "task": "example_task",
  "tags": "example_tags",
  "sort": "example_sort",
  "direction": "example_direction",
  "limit": 1,
  "offset": 1
}' --json

Use the provider shortcut form for shorter human-facing commands.

kosmo integrations:hugging-face huggingface_list_models '{
  "search": "example_search",
  "author": "example_author",
  "task": "example_task",
  "tags": "example_tags",
  "sort": "example_sort",
  "direction": "example_direction",
  "limit": 1,
  "offset": 1
}' --json

Agent Discovery Commands

These commands return structured output for coding agents that need to inspect capabilities before choosing a function.

kosmo integrations:docs hugging-face --json
kosmo integrations:docs hugging-face.huggingface_list_models --json
kosmo integrations:schema hugging-face.huggingface_list_models --json
kosmo integrations:search "Hugging Face" --json
kosmo integrations:list --json

All CLI Functions

Every function below can be called headlessly. The generic form is stable across all integrations; the provider shortcut is shorter but specific to Hugging Face.

`hugging-face.huggingface_list_models`

Read read

Search and list AI models on the Hugging Face Hub. Filter by text search, author, task (e.g. "text-generation", "image-classification"), tags, and sort by downloads, likes, or recent activity.

Parameters: search, author, task, tags, sort, direction, limit, offset

Generic CLI call

kosmo integrations:call hugging-face.huggingface_list_models '{"search":"example_search","author":"example_author","task":"example_task","tags":"example_tags","sort":"example_sort","direction":"example_direction","limit":1,"offset":1}' --json

Provider shortcut

kosmo integrations:hugging-face huggingface_list_models '{"search":"example_search","author":"example_author","task":"example_task","tags":"example_tags","sort":"example_sort","direction":"example_direction","limit":1,"offset":1}' --json

`hugging-face.huggingface_get_model`

Read read

Get detailed information about a specific Hugging Face model, including its card, tags, pipeline tag, library, downloads, likes, and file listing.

Parameters: model_id

Generic CLI call

kosmo integrations:call hugging-face.huggingface_get_model '{"model_id":"example_model_id"}' --json

Provider shortcut

kosmo integrations:hugging-face huggingface_get_model '{"model_id":"example_model_id"}' --json

`hugging-face.huggingface_list_datasets`

Read read

Search and list datasets on the Hugging Face Hub. Filter by text search, author, tags, and sort by downloads, likes, or recent activity.

Parameters: search, author, tags, sort, direction, limit, offset

Generic CLI call

kosmo integrations:call hugging-face.huggingface_list_datasets '{"search":"example_search","author":"example_author","tags":"example_tags","sort":"example_sort","direction":"example_direction","limit":1,"offset":1}' --json

Provider shortcut

kosmo integrations:hugging-face huggingface_list_datasets '{"search":"example_search","author":"example_author","tags":"example_tags","sort":"example_sort","direction":"example_direction","limit":1,"offset":1}' --json

`hugging-face.huggingface_inference`

Write write

Run inference on a Hugging Face model via the serverless Inference API. Supports text generation, summarization, translation, classification, image analysis, and more. The payload structure depends on the model's task — refer to the Hugging Face Inference API docs for model-specific formats.

Parameters: model_id, inputs, parameters, data

Generic CLI call

kosmo integrations:call hugging-face.huggingface_inference '{"model_id":"example_model_id","inputs":"example_inputs","parameters":"example_parameters","data":"example_data"}' --json

Provider shortcut

kosmo integrations:hugging-face huggingface_inference '{"model_id":"example_model_id","inputs":"example_inputs","parameters":"example_parameters","data":"example_data"}' --json

`hugging-face.huggingface_list_spaces`

Read read

Search and list Spaces on the Hugging Face Hub. Filter by text search, author, tags, SDK, and sort by downloads, likes, or recent activity.

Parameters: search, author, tags, sort, direction, limit, offset

Generic CLI call

kosmo integrations:call hugging-face.huggingface_list_spaces '{"search":"example_search","author":"example_author","tags":"example_tags","sort":"example_sort","direction":"example_direction","limit":1,"offset":1}' --json

Provider shortcut

kosmo integrations:hugging-face huggingface_list_spaces '{"search":"example_search","author":"example_author","tags":"example_tags","sort":"example_sort","direction":"example_direction","limit":1,"offset":1}' --json

`hugging-face.huggingface_get_current_user`

Read read

Get the authenticated Hugging Face user's profile information, including name, username, type (user/org), and avatar.

Parameters: none

Generic CLI call

kosmo integrations:call hugging-face.huggingface_get_current_user '{}' --json

Provider shortcut

kosmo integrations:hugging-face huggingface_get_current_user '{}' --json

Function Schemas

Use these parameter tables when building CLI payloads without calling integrations:schema first.

`hugging-face.huggingface_list_models`

Search and list AI models on the Hugging Face Hub. Filter by text search, author, task (e.g. "text-generation", "image-classification"), tags, and sort by downloads, likes, or recent activity.

Operation: Read read
Schema command: kosmo integrations:schema hugging-face.huggingface_list_models --json

Parameter	Type	Required	Description
`search`	string	no	Search query to filter models by name or description.
`author`	string	no	Filter by organization or user (e.g. "meta-llama", "openai").
`task`	string	no	Filter by pipeline task (e.g. "text-generation", "text-classification", "image-classification", "automatic-speech-recognition").
`tags`	array	no	Filter by tags (e.g. ["pytorch", "safetensors"]).
`sort`	string	no	Sort order: "downloads", "likes", "lastModified", "created". Defaults to "downloads".
`direction`	string	no	Sort direction: "asc" or "desc". Defaults to "desc".
`limit`	integer	no	Number of results per page (default: 20, max: 500).
`offset`	integer	no	Offset for pagination.

`hugging-face.huggingface_get_model`

Get detailed information about a specific Hugging Face model, including its card, tags, pipeline tag, library, downloads, likes, and file listing.

Operation: Read read
Schema command: kosmo integrations:schema hugging-face.huggingface_get_model --json

Parameter	Type	Required	Description
`model_id`	string	yes	The model ID (e.g. "meta-llama/Llama-3.3-70B-Instruct", "bert-base-uncased").

`hugging-face.huggingface_list_datasets`

Search and list datasets on the Hugging Face Hub. Filter by text search, author, tags, and sort by downloads, likes, or recent activity.

Operation: Read read
Schema command: kosmo integrations:schema hugging-face.huggingface_list_datasets --json

Parameter	Type	Required	Description
`search`	string	no	Search query to filter datasets by name or description.
`author`	string	no	Filter by organization or user (e.g. "HuggingFaceFW", "mozilla-foundation").
`tags`	array	no	Filter by tags (e.g. ["text-classification", "english"]).
`sort`	string	no	Sort order: "downloads", "likes", "lastModified", "created". Defaults to "downloads".
`direction`	string	no	Sort direction: "asc" or "desc". Defaults to "desc".
`limit`	integer	no	Number of results per page (default: 20, max: 500).
`offset`	integer	no	Offset for pagination.

`hugging-face.huggingface_inference`

Operation: Write write
Schema command: kosmo integrations:schema hugging-face.huggingface_inference --json

Parameter	Type	Required	Description
`model_id`	string	yes	The model ID to run inference on (e.g. "meta-llama/Llama-3.3-70B-Instruct", "facebook/bart-large-cnn").
`inputs`	string	no	The input text or data for the model. For text tasks, this is the prompt or text to process.
`parameters`	object	no	Model-specific parameters (e.g. {"max_new_tokens": 256, "temperature": 0.7, "top_p": 0.95} for text generation).
`data`	string	no	Base64-encoded data for image/audio tasks. Use this instead of "inputs" for non-text models.

`hugging-face.huggingface_list_spaces`

Search and list Spaces on the Hugging Face Hub. Filter by text search, author, tags, SDK, and sort by downloads, likes, or recent activity.

Operation: Read read
Schema command: kosmo integrations:schema hugging-face.huggingface_list_spaces --json

Parameter	Type	Required	Description
`search`	string	no	Search query to filter Spaces by name or description.
`author`	string	no	Filter by organization or user (e.g. "gradio", "stabilityai").
`tags`	array	no	Filter by tags (e.g. ["gradio", "text-generation"]).
`sort`	string	no	Sort order: "downloads", "likes", "lastModified", "created". Defaults to "downloads".
`direction`	string	no	Sort direction: "asc" or "desc". Defaults to "desc".
`limit`	integer	no	Number of results per page (default: 20, max: 500).
`offset`	integer	no	Offset for pagination.

`hugging-face.huggingface_get_current_user`

Get the authenticated Hugging Face user's profile information, including name, username, type (user/org), and avatar.

Operation: Read read
Schema command: kosmo integrations:schema hugging-face.huggingface_get_current_user --json

Parameter	Type	Required	Description
No parameters.

Permissions

Headless calls still follow the integration read/write permission policy. Configure read/write defaults with integrations:configure. Add --force only for trusted automation that should bypass that policy.