Hosting

remote or self-hosted

Transport

Streamable HTTP and stdio

Endpoint

https://huggingface.co/mcp

Authentication

Remote login flow or Hugging Face access token with READ permission; direct bearer token is supported. HTTP requests require Authorization: Bearer token.

Requirements

• Hugging Face account/token with READ permission for authenticated tools
• MCP-compatible client

Setup steps

1. Add remote endpoint https://huggingface.co/mcp using client native HTTP MCP support.
2. For Claude Code, use `claude mcp add hf-mcp-server -t http https://huggingface.co/mcp?login`, then start Claude and complete sign-in.
3. A direct-token configuration can use endpoint https://huggingface.co/mcp and Authorization: Bearer <HF_TOKEN>.
4. Self-hosted repository supports TRANSPORT=stdio or streamableHttpJson; HTTP clients send a Hugging Face bearer token.

Current unauthenticated tools/list returned these four base tools. The official server supports optional auth and query-selected bouquets/mixes that can expose additional tools; authenticated/configured variants are not included in this base snapshot.

• hf_whoami

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

  01
• 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. Include links to repositories in your response.

  Parameters: query, repo_types, author, filters, sort, limit
  02
• 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: repo_ids, repo_type, operations, config, split, offset, limit
  03
• hf_fs

  When to use: Hugging Face Hub models, datasets, Spaces, collections, papers, daily papers, today's trending models, current paper leaderboard, docs, and repository files. Examples: {"operations":[{"cmd":"ls","args":["hf://models/trending","--limit","10"]}]} {"operations":[{"cmd":"ls","args":["hf://papers/trending"]}]} {"operations":[{"cmd":"ls","args":["hf://papers/daily/latest"]}]} {"operations":[{"cmd":"cat","args":["hf://papers/2501.00001/paper.md"]}]} {"operations":[{"cmd":"search","args":["hf://models","--tag","base_model:finetune:org/repo"]}]} Use hf_fs for Hugging Face Hub filesystem operations. Call it with operations, an array of {cmd, args} items; multiple operations may be submitted together. Usage: {"operations":[{"cmd":"ls","args":["hf://models/org/repo"]}]} Grammar; each string below is one args array item: ls URI [--recursive] [--glob GLOB] [--type TYPE] [--sort SORT] [--limit N] cat URI [--offset N] [--max-bytes N] attach URI [--max-bytes N] stat URI find URI [--name GLOB] [--path GLOB] [--type TYPE] [--limit N] search URI [QUERY] [--type TYPE] [--sort SORT] [--tag TAG] [--kind mcp] [--limit N] COMMAND = ls|cat|attach|stat|find|search. TYPE = file|dir|repo|bucket|collection|paper|link. SORT = createdAt|downloads|likes|lastModified|likes30d|trendingScore|mainSize|id|trending|upvotes. URI is a canonical hf:// URI. QUERY and GLOB are each one string. Use search for resource discovery, not repository-content search; ls for a known directory, find for recursive file discovery by name/path (not file contents), stat for filesystem metadata or an uncertain target type, cat for text contents, and attach for a complete JPEG, PNG, or WebP image. When the request gives an exact text-file URI, use cat directly; do not add ls or stat first. stat does not read the contents of JSON, Markdown, or other text files. Search scopes: hf://models[/OWNER], hf://datasets[/OWNER], hf://spaces[/OWNER], hf://collections[/OWNER],…

  Parameters: operations
  04

• Tool set is user-configurable/dynamic.
• A valid Hugging Face token with READ permission is needed for MCP tools per official Hub docs.

• official maintainer repository

  Current repository docs explain the default anonymous tool set, optional Hugging Face authentication, dynamic tool bundles, and server configuration.

• live runtime tools list

  An unauthenticated initialize/tools/list request returned four tools at server version 0.4.31 on the checked date.

• official hub documentation

  Publisher docs describe Hugging Face token requirements for authenticated Hub operations.

Documentation checked 2026-10-28T13:41:09.000Z. Connection has not been runtime tested.