ModelsAtlas
Explore
Atlas / MCP servers / shreyaskarnik / Hugging Face

Hugging FaceSAFE

mcp/shreyaskarnik/hugging-face
MCP server by shreyaskarnik · Audited 2026-10-07
⚑ Report / re-scanSource ↗
Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
10 10r · 0w · 0d
Transport
stdio
License
MIT
Stars
72
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://smithery.ai/server/@shreyaskarnik/huggingface-mcp-server)

A Model Context Protocol (MCP) server that provides read-only access to the Hugging Face Hub APIs. This server allows LLMs like Claude to interact with Hugging Face's models, datasets, spaces, papers, and collections.

Components

Resources

The server exposes popular Hugging Face resources:

  • Custom hf:// URI scheme for accessing resources
  • Models with hf://model/{model_id} URIs
  • Datasets with hf://dataset/{dataset_id} URIs
  • Spaces with hf://space/{space_id} URIs
  • All resources have descriptive names and JSON content type

Prompts

The server provides two prompt templates:

  • compare-models: Generates a comparison between multiple Hugging Face models
  • Required model_ids argument (comma-separated model IDs)
  • Retrieves model details and formats them for comparison
  • summarize-paper: Summarizes a research paper from Hugging Face
  • Required arxiv_id argument for paper identification
  • Optional detail_level argument (brief/detailed) to control summary depth
  • Combines paper metadata with implementation details

Tools

The server implements several tool categories:

  • Model Tools
  • search-models: Search models with filters for query, author, tags, and limit
  • get-model-info: Get detailed information about a specific model
  • Dataset Tools
  • search-datasets: Search datasets with filters
  • get-dataset-info: Get detailed information about a specific dataset
  • Space Tools
  • search-spaces: Search Spaces with filters including SDK type
  • get-space-info: Get detailed information about a specific Space
  • Paper Tools
  • get-paper-info: Get information about a paper and its implementations
  • get-daily-papers: Get the list of curated daily papers
  • Collection Tools
  • search-collections: Search c
Read from source at commit 827644f0ce17OBSERVED · 2026-10-07
Advertisement
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add huggingface -- uvx huggingface
claude-desktop
{
  "mcpServers": {
    "huggingface": {
      "command": "uvx",
      "args": [
        "huggingface"
      ]
    }
  }
}
03

Exposed tools (10)

10 read · 0 write · 0 destructive.

ToolRiskDescription
get-collection-inforeadGet detailed information about a specific collection
get-daily-papersreadGet the list of daily papers curated by Hugging Face
get-dataset-inforeadGet detailed information about a specific dataset
get-model-inforeadGet detailed information about a specific model
get-paper-inforeadGet information about a specific paper on Hugging Face
get-space-inforeadGet detailed information about a specific Space
search-collectionsreadSearch for collections on Hugging Face Hub
search-datasetsreadSearch for datasets on Hugging Face Hub
search-modelsreadSearch for models on Hugging Face Hub
search-spacesreadSearch for Spaces on Hugging Face Hub
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
declared (1 observation(s))
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.

Audited 2026-10-07 · audit v0.4.1 · source sha 827644f0ce17full audit observations/trust-audit/mcp-server/shreyaskarnik__hugging-face.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-07827644f0ce17SAFEB89first audit
06

Questions

What tools does Hugging Face expose?

10 in total: 10 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Hugging Face safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Hugging Face need?

No credential environment variables were found in its source, so it appears to need none.

How does Hugging Face run?

It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as huggingface.

How current is this page?

The grade is for one exact copy of the source (827644f0ce17), read on 2026-10-07. The repository is watched and re-audited when it changes.

Advertisement