co.huggingface/hf-mcp-server

Official8 tools

Hugging Face

Connect to Hugging Face Hub and thousands of Gradio AI Applications

Connect to Hugging Face Hub and run thousands of Gradio-based AI applications.

Captured live from the server via tools/list.

hf_whoami

Hugging Face tools are being used anonymously and may be rate limited. Call this tool for instructions on joining and authenticating.

No parameters.

space_search

Find Hugging Face Spaces using semantic search. IMPORTANT Only MCP Servers can be used with the dynamic_space toolInclude links to the Space when presenting the results.

Parameters (3)

querystringrequired
Semantic Search Query
limitnumber
Number of results to return
mcpboolean
Only return MCP Server enabled Spaces

hub_repo_search

Search Hugging Face repositories with a shared query interface. You can target models, datasets, spaces, or aggregate across multiple repo types in one call. Use space_search for semantic-first discovery of Spaces. Include links to repositories in your response.

Parameters (6)

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

paper_search

Find Machine Learning research papers on the Hugging Face hub. Include 'Link to paper' When presenting the results. Consider whether tabulating results matches user intent.

Parameters (3)

querystringrequired
Semantic Search query
results_limitnumber
Number of results to return
concise_onlyboolean
Return a 2 sentence summary of the abstract. Use for broad search terms which may return a lot of results. Check with User if unsure.

hub_repo_details

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.

Parameters (7)

repo_idsarrayrequired
Repo IDs for (models|dataset/space) - usually in author/name format (e.g. openai/gpt-oss-120b)
repo_typestring
Specify lookup type; otherwise auto-detects
operationsarray
Details to return. Defaults to ["overview"]. For datasets, prefer ["overview", "dataset_structure"] first; then call ["dataset_preview"] with config and split.
configstring
Dataset Viewer config. Required for dataset_preview when the dataset has multiple config/split options. Discover via dataset_structure.
splitstring
Dataset Viewer split. Required for dataset_preview when the dataset has multiple config/split options. Discover via dataset_structure.
offsetinteger
Row offset for dataset_preview. Defaults to 0.
limitinteger
Row count for dataset_preview. Defaults to 5 and is clamped to 1-100.

hf_fs

List or read files from a Hugging Face repo or bucket. Anonymous requests must include an owner.

Parameters (8)

opstringrequired
uristringrequired
Hugging Face URI in the form hf://models|datasets|spaces|buckets/OWNER[/NAME[/PATH]].
globstring
recursiveboolean
entry_typestring
max_bytesinteger
cat max read length. 0 means the maximum allowed 80000 bytes.
offsetinteger
cat read start offset.
limitinteger
ls max list size. Default 1000. 0 means the maximum allowed 10000.

hf_doc_search

Search and Discover Hugging Face Product and Library documentation. Send an empty query to discover structure and navigation instructions. Knowledge up-to-date as at 3 July 2026. Combine with the Product filter to focus results.

Parameters (2)

querystringrequired
Start with an empty query for structure, endpoint discovery and navigation tips. Use semantic queries for targetted searches.
productstring
Filter by Product. Supply when known for focused results

hf_doc_fetch

Fetch a document from the Hugging Face or Gradio documentation library. For large documents, use offset to get subsequent chunks.

Parameters (2)

doc_urlstringrequired
Documentation URL (Hugging Face or Gradio)
offsetnumber
Token offset for large documents (use the offset from truncation message)

Install

claude_desktop_config.json

{
  "mcpServers": {
    "hf-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://huggingface.co/mcp?login"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.