Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Hugging Face

REMOTE · HUGGINGFACE.CO · 2 COMPONENTS · SCANNED SEP 20

Connect to Hugging Face Hub and thousands of Gradio AI Applications

0 this week 83 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security83
Transport & Reachability100
Schema Quality & AI Usability56
  • 16% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Partial
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 5569 tokens (~35/item across 159 items; 4 tools + 155 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management88
  • Stability check failed: schema churn in the 30 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 0 additions. See how to fix → Fail
Tool Coverage98
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 93% of tool parameters carry a description.Partial
  • Structured output schemas are declared (50% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Install

How do I install the Hugging Face MCP server?

Hugging Face is a hosted endpoint at https://huggingface.co/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · huggingface.co

# add to Claude Code
claude mcp add --transport http co-huggingface-hf-mcp-server 'https://huggingface.co/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "co-huggingface-hf-mcp-server": {
      "url": "https://huggingface.co/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "co-huggingface-hf-mcp-server": {
      "type": "http",
      "url": "https://huggingface.co/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.co-huggingface-hf-mcp-server]
url = "https://huggingface.co/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "co-huggingface-hf-mcp-server": {
      "type": "remote",
      "url": "https://huggingface.co/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add co-huggingface-hf-mcp-server --url 'https://huggingface.co/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  co-huggingface-hf-mcp-server:
    url: "https://huggingface.co/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "co-huggingface-hf-mcp-server": {
      "Transport": "http",
      "Url": "https://huggingface.co/mcp"
    }
  }
}
# add to Vellum
assistant mcp add co-huggingface-hf-mcp-server -t streamable-http -u 'https://huggingface.co/mcp'
// mcp.json
{
  "mcpServers": {
    "co-huggingface-hf-mcp-server": {
      "type": "http",
      "url": "https://huggingface.co/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 0
    • Resource “estimate_cost.py” now points somewhere else: skill://huggingface-llm-trainer/scripts/estimate_cost.py → skill://huggingface-vision-trainer/scripts/estimate_cost.py security
    • Resource “hardware_guide.md” now points somewhere else: skill://huggingface-llm-trainer/references/hardware_guide.md → skill://train-sentence-transformers/references/hardware_guide.md security
    • Resource “hub_saving.md” now points somewhere else: skill://huggingface-llm-trainer/references/hub_saving.md → skill://huggingface-vision-trainer/references/hub_saving.md security
    • Resource “dataset_inspector.py” now points somewhere else: skill://huggingface-llm-trainer/scripts/dataset_inspector.py → skill://huggingface-vision-trainer/scripts/dataset_inspector.py security
    • Resource “reliability_principles.md” now points somewhere else: skill://huggingface-llm-trainer/references/reliability_principles.md → skill://huggingface-vision-trainer/references/reliability_principles.md security
    • Resource “troubleshooting.md” now points somewhere else: skill://huggingface-llm-trainer/references/troubleshooting.md → skill://train-sentence-transformers/references/troubleshooting.md security
  • 19 Sept 26 0
    • Resource “dataset_inspector.py” now points somewhere else: skill://huggingface-llm-trainer/scripts/dataset_inspector.py → skill://huggingface-vision-trainer/scripts/dataset_inspector.py security
    • Resource “estimate_cost.py” now points somewhere else: skill://huggingface-llm-trainer/scripts/estimate_cost.py → skill://huggingface-vision-trainer/scripts/estimate_cost.py security
    • Resource “hardware_guide.md” now points somewhere else: skill://huggingface-llm-trainer/references/hardware_guide.md → skill://train-sentence-transformers/references/hardware_guide.md security
    • Resource “hub_saving.md” now points somewhere else: skill://huggingface-llm-trainer/references/hub_saving.md → skill://huggingface-vision-trainer/references/hub_saving.md security
    • Resource “reliability_principles.md” now points somewhere else: skill://huggingface-llm-trainer/references/reliability_principles.md → skill://huggingface-vision-trainer/references/reliability_principles.md security
    • Resource “troubleshooting.md” now points somewhere else: skill://huggingface-llm-trainer/references/troubleshooting.md → skill://train-sentence-transformers/references/troubleshooting.md security
  • 18 Sept 26 0
    • Resource “dataset_inspector.py” now points somewhere else: skill://huggingface-llm-trainer/scripts/dataset_inspector.py → skill://huggingface-vision-trainer/scripts/dataset_inspector.py security
    • Resource “estimate_cost.py” now points somewhere else: skill://huggingface-llm-trainer/scripts/estimate_cost.py → skill://huggingface-vision-trainer/scripts/estimate_cost.py security
    • Resource “hardware_guide.md” now points somewhere else: skill://huggingface-llm-trainer/references/hardware_guide.md → skill://train-sentence-transformers/references/hardware_guide.md security
    • Resource “hub_saving.md” now points somewhere else: skill://huggingface-llm-trainer/references/hub_saving.md → skill://huggingface-vision-trainer/references/hub_saving.md security
    • Resource “reliability_principles.md” now points somewhere else: skill://huggingface-llm-trainer/references/reliability_principles.md → skill://huggingface-vision-trainer/references/reliability_principles.md security
    • Resource “troubleshooting.md” now points somewhere else: skill://huggingface-llm-trainer/references/troubleshooting.md → skill://train-sentence-transformers/references/troubleshooting.md security
  • 17 Sept 26 0
    • Resource “dataset_inspector.py” now points somewhere else: skill://huggingface-llm-trainer/scripts/dataset_inspector.py → skill://huggingface-vision-trainer/scripts/dataset_inspector.py security
    • Resource “estimate_cost.py” now points somewhere else: skill://huggingface-llm-trainer/scripts/estimate_cost.py → skill://huggingface-vision-trainer/scripts/estimate_cost.py security
    • Resource “hardware_guide.md” now points somewhere else: skill://huggingface-llm-trainer/references/hardware_guide.md → skill://train-sentence-transformers/references/hardware_guide.md security
    • Resource “hub_saving.md” now points somewhere else: skill://huggingface-llm-trainer/references/hub_saving.md → skill://huggingface-vision-trainer/references/hub_saving.md security
    • Resource “reliability_principles.md” now points somewhere else: skill://huggingface-llm-trainer/references/reliability_principles.md → skill://huggingface-vision-trainer/references/reliability_principles.md security
    • Resource “troubleshooting.md” now points somewhere else: skill://huggingface-llm-trainer/references/troubleshooting.md → skill://train-sentence-transformers/references/troubleshooting.md security
    • Server version: 0.4.19 → 0.4.20 functional
  • 16 Sept 26 0
    • Resource “dataset_inspector.py” now points somewhere else: skill://huggingface-llm-trainer/scripts/dataset_inspector.py → skill://huggingface-vision-trainer/scripts/dataset_inspector.py security
    • Resource “estimate_cost.py” now points somewhere else: skill://huggingface-llm-trainer/scripts/estimate_cost.py → skill://huggingface-vision-trainer/scripts/estimate_cost.py security
    • Resource “hardware_guide.md” now points somewhere else: skill://huggingface-llm-trainer/references/hardware_guide.md → skill://train-sentence-transformers/references/hardware_guide.md security
    • Resource “hub_saving.md” now points somewhere else: skill://huggingface-llm-trainer/references/hub_saving.md → skill://huggingface-vision-trainer/references/hub_saving.md security
    • Resource “reliability_principles.md” now points somewhere else: skill://huggingface-llm-trainer/references/reliability_principles.md → skill://huggingface-vision-trainer/references/reliability_principles.md security
    • Resource “troubleshooting.md” now points somewhere else: skill://huggingface-llm-trainer/references/troubleshooting.md → skill://train-sentence-transformers/references/troubleshooting.md security
  • 15 Sept 26 0
    • Resource “dataset_inspector.py” now points somewhere else: skill://huggingface-llm-trainer/scripts/dataset_inspector.py → skill://huggingface-vision-trainer/scripts/dataset_inspector.py security
    • Resource “estimate_cost.py” now points somewhere else: skill://huggingface-llm-trainer/scripts/estimate_cost.py → skill://huggingface-vision-trainer/scripts/estimate_cost.py security
    • Resource “hardware_guide.md” now points somewhere else: skill://huggingface-llm-trainer/references/hardware_guide.md → skill://train-sentence-transformers/references/hardware_guide.md security
    • Resource “hub_saving.md” now points somewhere else: skill://huggingface-llm-trainer/references/hub_saving.md → skill://huggingface-vision-trainer/references/hub_saving.md security
    • Resource “reliability_principles.md” now points somewhere else: skill://huggingface-llm-trainer/references/reliability_principles.md → skill://huggingface-vision-trainer/references/reliability_principles.md security
    • Resource “troubleshooting.md” now points somewhere else: skill://huggingface-llm-trainer/references/troubleshooting.md → skill://train-sentence-transformers/references/troubleshooting.md security
  • 14 Sept 26 0
    • Resource “dataset_inspector.py” now points somewhere else: skill://huggingface-llm-trainer/scripts/dataset_inspector.py → skill://huggingface-vision-trainer/scripts/dataset_inspector.py security
    • Resource “estimate_cost.py” now points somewhere else: skill://huggingface-llm-trainer/scripts/estimate_cost.py → skill://huggingface-vision-trainer/scripts/estimate_cost.py security
    • Resource “hardware_guide.md” now points somewhere else: skill://huggingface-llm-trainer/references/hardware_guide.md → skill://train-sentence-transformers/references/hardware_guide.md security
    • Resource “hub_saving.md” now points somewhere else: skill://huggingface-llm-trainer/references/hub_saving.md → skill://huggingface-vision-trainer/references/hub_saving.md security
    • Resource “reliability_principles.md” now points somewhere else: skill://huggingface-llm-trainer/references/reliability_principles.md → skill://huggingface-vision-trainer/references/reliability_principles.md security
    • Resource “troubleshooting.md” now points somewhere else: skill://huggingface-llm-trainer/references/troubleshooting.md → skill://train-sentence-transformers/references/troubleshooting.md security
  • 13 Sept 26 0
    • Resource “dataset_inspector.py” now points somewhere else: skill://huggingface-llm-trainer/scripts/dataset_inspector.py → skill://huggingface-vision-trainer/scripts/dataset_inspector.py security
    • Resource “estimate_cost.py” now points somewhere else: skill://huggingface-llm-trainer/scripts/estimate_cost.py → skill://huggingface-vision-trainer/scripts/estimate_cost.py security
    • Resource “hardware_guide.md” now points somewhere else: skill://huggingface-llm-trainer/references/hardware_guide.md → skill://train-sentence-transformers/references/hardware_guide.md security
    • Resource “hub_saving.md” now points somewhere else: skill://huggingface-llm-trainer/references/hub_saving.md → skill://huggingface-vision-trainer/references/hub_saving.md security
    • Resource “reliability_principles.md” now points somewhere else: skill://huggingface-llm-trainer/references/reliability_principles.md → skill://huggingface-vision-trainer/references/reliability_principles.md security
    • Resource “troubleshooting.md” now points somewhere else: skill://huggingface-llm-trainer/references/troubleshooting.md → skill://train-sentence-transformers/references/troubleshooting.md security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Probed https://huggingface.co/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=huggingface.co CN=Amazon RSA 2048 M01,O=Amazon,C=US 14 Aug 2026 27 Feb 2027 RSA 2048 SHA256-RSA d7f89cd943c09c5aa9c7a1d94c755c4
SANs: huggingface.co, *.huggingface.co
CN=Amazon RSA 2048 M01,O=Amazon,C=US (CA) CN=Amazon Root CA 1,O=Amazon,C=US 23 Aug 2022 23 Aug 2030 RSA 2048 SHA256-RSA 77312380b9d6688a33b1ed9bf9ccda68e0e0f
CN=Amazon Root CA 1,O=Amazon,C=US (CA) CN=Starfield Services Root Certificate Authority - G2,O=Starfield Technologies\, Inc.,L=Scottsdale,ST=Arizona,C=US 25 May 2015 31 Dec 2037 RSA 2048 SHA256-RSA 67f944a2a27cdf3fac2ae2b01f908eeb9c4c6

Background: What to check on a remote MCP endpoint →

DNSSEC secure

Validation of huggingface.co. Secure

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
co. present 7786 8 Verified
huggingface.co. present 34884 13 Verified
huggingface.co. Verified address RRset verified with the apex keys
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000
x-content-type-options nosniff
referrer-policy no-referrer

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://huggingface.co/mcp Verified 200
http (plaintext) http://huggingface.co/mcp HTTPS enforced 301 https://huggingface.co/mcp
MCP tools · 4 exposed · ~1,276 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
hf_fs ~749

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"]}]} 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], hf://papers, and hf://docs[/...]. Repository and repository-file scopes are not supported: search a reso…

NameTypeReqDescription
operationsarrayyes
NameTypeReqDescription
resultsarrayyes
truncatedboolean
truncation_reasonstring

No examples provided.

hf_whoami ~40

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

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

hub_repo_details ~279

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.

NameTypeReqDescription
configstringDataset Viewer config. Required for dataset_preview when the dataset has multiple config/split options. Discover via dataset_structure.
limitintegerRow count for dataset_preview. Defaults to 5 and is clamped to 1-100.
offsetintegerRow offset for dataset_preview. Defaults to 0.
operationsarrayDetails to return. Defaults to ["overview"]. For datasets, prefer ["overview", "dataset_structure"] first; then call ["dataset_preview"] with config and split.
repo_idsarrayyesRepo IDs for (models|dataset/space) - usually in author/name format (e.g. openai/gpt-oss-120b)
repo_typestringSpecify lookup type; otherwise auto-detects
splitstringDataset Viewer split. Required for dataset_preview when the dataset has multiple config/split options. Discover via dataset_structure.

No output schema declared.

No examples provided.

hub_repo_search ~208

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.

NameTypeReqDescription
authorstringOrganization or user namespace to filter by (e.g. 'google', 'meta-llama', 'huggingface').
filtersarrayOptional hub filter tags. Applied to each selected repo type (e.g. ["text-generation"], ["language:en"], ["mcp-server"]).
limitnumberMaximum number of results to return per selected repo type
querystringSearch term. Leave blank and specify sort + limit to browse trending or recent repositories.
repo_typesarrayRepository types to search. Defaults to ["model", "dataset"]. space uses keyword search via /api/spaces.
sortstringSort order (descending): trendingScore, downloads, likes, createdAt, lastModified

No output schema declared.

No examples provided.

Common questions

What is the Hugging Face MCP server?

Hugging Face is an MCP server listed in the public MCP registry as co.huggingface/hf-mcp-server. Connect to Hugging Face Hub and thousands of Gradio AI Applications. This page covers its hosted endpoint (https://huggingface.co/mcp).

Is the Hugging Face MCP server safe to use?

Hugging Face scores 83 out of 100 on VerifyMCP. 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 Hugging Face MCP server expose?

Hugging Face exposes 4 tools: hf_whoami, hub_repo_search, hub_repo_details, hf_fs. Their descriptions and schemas cost roughly 1,276 tokens of context every time the server is loaded.

Does the Hugging Face MCP server require authentication?

No. We connected to Hugging Face without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Hugging Face MCP server still maintained?

Hugging Face is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.