# Huggingface (npm · @pipeworx/mcp-huggingface)

Hugging Face Hub MCP — models, datasets, spaces

- Trust score: 83/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `gateway.pipeworx.io`: 77/100, [markdown](https://verifymcp.io/servers/pipeworx-io-huggingface/huggingface-mcp.md), [page](https://verifymcp.io/servers/pipeworx-io-huggingface/huggingface-mcp)
- npm · `@pipeworx/mcp-huggingface`: 83/100 (this document), [markdown](https://verifymcp.io/servers/pipeworx-io-huggingface/pipeworx-mcp-huggingface.md), [page](https://verifymcp.io/servers/pipeworx-io-huggingface/pipeworx-mcp-huggingface)

## Channel facts

- Registry: `npm`
- Package: `@pipeworx/mcp-huggingface`
- Version: `0.2.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to pipeworx-io/mcp-huggingface).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 74/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 931 tokens (~93/item across 10 items; 10 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 83/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 49% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Huggingface MCP server?

Huggingface runs locally as an npm package, launched with npx -y @pipeworx/mcp-huggingface. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add pipeworx-io-huggingface -- npx -y @pipeworx/mcp-huggingface
```

### Cursor

```json
{
  "mcpServers": {
    "pipeworx-io-huggingface": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-huggingface"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "pipeworx-io-huggingface": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-huggingface"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add pipeworx-io-huggingface -- npx -y @pipeworx/mcp-huggingface
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "pipeworx-io-huggingface": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@pipeworx/mcp-huggingface"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add pipeworx-io-huggingface --command npx --arg -y --arg @pipeworx/mcp-huggingface
```

### Hermes

```yaml
mcp_servers:
  pipeworx-io-huggingface:
    command: "npx"
    args: ["-y", "@pipeworx/mcp-huggingface"]
```

### Netclaw

```json
{
  "McpServers": {
    "pipeworx-io-huggingface": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@pipeworx/mcp-huggingface"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add pipeworx-io-huggingface -t stdio -c npx -a -y @pipeworx/mcp-huggingface
```

### Other

```json
{
  "mcpServers": {
    "pipeworx-io-huggingface": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-huggingface"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 82, +27)

- [security improvement] Malware scan: unverified → pass
- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → pass

### 2026-11-02 (score 55, −24)

- [security regression] Malware scan: pass → unverified
- [security regression] Known CVEs: pass → unverified
- [functional regression] Security disclosure: unverified → fail
- [functional regression] Dependency health: pass → unverified
- [functional improvement] Stability: unverified → 0.13
- [functional] Package version: 0.2.0 → 0.2.1

### 2026-11-01 (score 79, 0)

- [functional regression] Security disclosure: fail → unverified

### 2026-10-30 (score 79, 0)

- [functional regression] Security disclosure: unverified → fail

### 2026-10-29 (score 79)

First indexed and scored.

## MCP tools (10)

### `search_models` (~229 tokens)

Search Hugging Face Hub models with filters for author, library (transformers/diffusers/…), language, pipeline_tag (text-generation/…), and tags; sort by downloads, likes, or trendingScore.

Input parameters:

- `author` (string): Filter by org or user (e.g. "meta-llama")
- `direction` (string): -1 (desc, default) | 1 (asc)
- `full` (boolean): Include extra fields (cardData, gated, etc.)
- `language` (string): ISO language code, e.g. "fr" — matched as a Hub tag, not validated
- `library` (string): transformers | diffusers | sentence-transformers | ...
- `limit` (number): 1-1000 (default 20)
- `pipeline_tag` (string): text-generation | text-classification | image-classification | translation | ...
- `search` (string): Free-text — name / description
- `sort` (string): downloads | likes | trendingScore | lastModified | createdAt
- `tags` (string): Comma-separated tags

### `search_datasets` (~126 tokens)

Search Hugging Face Hub datasets with filters for author, language, and task_categories; sort by downloads, likes, or lastModified; returns dataset id, downloads, likes, and tags.

Input parameters:

- `author` (string)
- `direction` (string)
- `full` (boolean)
- `language` (string): ISO language code, e.g. "fr"
- `limit` (number)
- `search` (string)
- `sort` (string)
- `task_categories` (string): Comma-separated task categories, e.g. "question-answering"

### `search_spaces` (~102 tokens)

Search Hugging Face Spaces (demo apps) with filters for author and SDK (gradio/streamlit/docker/static); returns space id, sdk, runtime status, and likes.

Input parameters:

- `author` (string)
- `direction` (string)
- `full` (boolean)
- `limit` (number)
- `sdk` (string): gradio | streamlit | docker | static
- `search` (string)
- `sort` (string)

### `get_model` (~56 tokens)

Detailed model info — config, tags, downloads, files at root.

Input parameters:

- `repo_id` (string, required): <author>/<repo> or <repo> for HF-owned
- `revision` (string): Branch/commit/tag (default main)

### `get_dataset` (~59 tokens)

Detailed Hugging Face dataset metadata by repo_id (e.g. "squad") and optional revision; returns card data, tags, downloads, task categories, and file list.

Input parameters:

- `repo_id` (string, required)
- `revision` (string)

### `get_space` (~62 tokens)

Detailed Hugging Face Space metadata by repo_id (e.g. "stabilityai/stable-diffusion") and optional revision; returns sdk, runtime status, likes, and linked models.

Input parameters:

- `repo_id` (string, required)
- `revision` (string)

### `list_model_files` (~121 tokens)

Hugging Face Hub API — list the files in a model repository at a given revision (branch, tag or commit; main by default) and optional subdirectory path. Returns each entry's path, type, byte size and blob SHA, including LFS details for weight shards. Answers which weight, config and tokenizer files ship in a Hugging Face model repo and how large they are.

Input parameters:

- `path` (string): Subdirectory (default root)
- `repo_id` (string, required)
- `revision` (string): Branch/commit/tag (default main)

### `list_dataset_files` (~62 tokens)

List files in a Hugging Face dataset repository by repo_id and optional revision/subdirectory path; returns filename, size, and blob SHA for each file.

Input parameters:

- `path` (string)
- `repo_id` (string, required)
- `revision` (string)

### `trending_models` (~31 tokens)

Currently-trending models on the Hub.

Input parameters:

- `limit` (number): 1-100 (default 20)

### `trending_datasets` (~29 tokens)

Currently-trending datasets.

Input parameters:

- `limit` (number): 1-100 (default 20)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/pipeworx-io-huggingface/pipeworx-mcp-huggingface#diagnostics

## Score history

- 2026-11-05: 83
- 2026-11-04: 82
- 2026-11-03: 82
- 2026-11-02: 55
- 2026-11-01: 79
- 2026-10-31: 79
- 2026-10-30: 79
- 2026-10-29: 79

## Common questions

### What is the Huggingface MCP server?

Huggingface is an MCP server listed in the public MCP registry as io.github.pipeworx-io/huggingface. Hugging Face Hub MCP, models, datasets, spaces. This page covers its npm package (@pipeworx/mcp-huggingface).

### Is the Huggingface MCP server safe to use?

Huggingface scores 83 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Huggingface MCP server expose?

Huggingface exposes 10 tools: search_models, search_datasets, search_spaces, get_model, get_dataset, and 5 more. Their descriptions and schemas cost roughly 877 tokens of context every time the server is loaded.

### Is the Huggingface MCP server still maintained?

Huggingface is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Huggingface MCP server under?

Huggingface declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@pipeworx/mcp-huggingface
- Socket report: https://socket.dev/npm/package/@pipeworx/mcp-huggingface
- Repository: https://github.com/pipeworx-io/mcp-huggingface
- Website: https://pipeworx.io/packs/huggingface
- Changelog RSS feed: https://verifymcp.io/servers/pipeworx-io-huggingface/pipeworx-mcp-huggingface.xml
- Changelog JSON feed: https://verifymcp.io/servers/pipeworx-io-huggingface/pipeworx-mcp-huggingface.json
- HTML version of this page: https://verifymcp.io/servers/pipeworx-io-huggingface/pipeworx-mcp-huggingface