Hugging Face, verified
MCP server by Hugging Face · Verified
Search Hugging Face Hub models, datasets, Spaces and papers, and browse repo files and trending lists from your assistant.
Connect to Hugging Face
Sign-in is optional. Connect with Hugging Face’s own URL:
It works without signing in. Sign in with Hugging Face for more access.
Share this server
Opens this page, with the URL and setup steps.
mcp.tc/i/hugging-faceAbout
Connects to the Hugging Face Hub so an assistant can search models, datasets, Spaces, collections, papers and docs, inspect repository details and dataset structure, and read files through hf:// paths. It can also list trending models, datasets, Spaces and daily papers. The registry entry also describes access to Gradio applications.
Runs as a hosted streamable HTTP endpoint at https://huggingface.co/mcp. It works anonymously with rate limits. Adding ?login starts OAuth sign-in, or you can send an Authorization Bearer header with a Hugging Face token for higher limits.
What you can do
- Search models, datasets and Spaces by query, author, filters and sort
- Get details for repos, including dataset structure and previews
- List trending models, datasets, Spaces and papers
- Read daily papers and paper content
- Read files from Hub repos via hf:// paths
- Check the current Hugging Face account and organizations
Tools 4
hf_whoamiRead-onlyShow the current Hugging Face account, organizations and credential access without revealing…
hub_repo_searchRead-onlySearch models, datasets or Spaces with query, author, filters, sort and limit.
hub_repo_detailsRead-onlyGet details for repos, including dataset structure and previews.
hf_fsRead-onlyRun ls, cat and search over hf:// paths for models, datasets, Spaces, papers and docs.
Read from the live server on 17 Nov 2026. Read-only, Writes and Can delete are hints the server declares; your client decides whether to ask before running a tool.
Example prompts
Show me today's trending models on Hugging Face
Find text-to-image Spaces and link to the top results
Show the structure and a preview of the squad dataset
List the latest daily papers on Hugging Face
Set up
Every client connects to huggingface.co. Pick yours; the page remembers your choice.
Claude Code
- Run this in a terminal, in your project folder:
claude mcp add --transport http hugging-face https://huggingface.co/mcp- Start Claude Code and type
/mcp. hugging-face should show as connected. To sign in for more access, pick it and choose Authenticate.
Add --scope user to make it available in every project, not just this one. Works without a key. An API key from Hugging Face raises the limits: send it as Authorization: Bearer <YOUR_API_KEY>.
Claude Desktop
- Open Customize → Connectors, click + Add, then Add custom connector.
- Name it Hugging Face and paste this URL:
https://huggingface.co/mcp- Click Add, then Connect. Signing in to Hugging Face is optional.
Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.
claude.ai
- Open the connector form on claude.ai. This button fills in the name and URL for you:
Add to claude.ai (opens in a new tab)
- Check that the URL reads
https://huggingface.co/mcpand click Add. - Click Connect. Signing in to Hugging Face is optional.
Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under Organization settings → Connectors.
ChatGPT
- On chatgpt.com, go to Plugins, select +, then Add custom MCP server.
- Enter a name for the server.
- Under Connection, paste
https://huggingface.co/mcpas the server URL, then for authentication choose No authentication, or OAuth to sign in to Hugging Face for more access. - Check I understand and want to continue, then select Create as a plugin.
Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).
Cursor
Add to Cursor (opens in a new tab)
Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):
{
"mcpServers": {
"hugging-face": {
"url": "https://huggingface.co/mcp"
}
}
}Works without a key. An API key from Hugging Face raises the limits: send it as Authorization: Bearer <YOUR_API_KEY>.
VS Code
Install in VS Code (opens in a new tab)
Or from a terminal:
code --add-mcp '{"name":"hugging-face","type":"http","url":"https://huggingface.co/mcp"}'Or commit it to the repo in .vscode/mcp.json:
{
"servers": {
"hugging-face": {
"type": "http",
"url": "https://huggingface.co/mcp"
}
}
}Works without a key. An API key from Hugging Face raises the limits: send it as Authorization: Bearer <YOUR_API_KEY>.
Devin Desktop
- Add it to
~/.config/devin/mcp_config.json(macOS and Linux) or%APPDATA%\devin\mcp_config.json(Windows):
{
"mcpServers": {
"hugging-face": {
"serverUrl": "https://huggingface.co/mcp"
}
}
}- Refresh the MCP server list in Cascade.
Devin Desktop is the new name for Windsurf. It reads serverUrl (or url) for remote servers. Works without a key. An API key from Hugging Face raises the limits: send it as Authorization: Bearer <YOUR_API_KEY>.
Codex
codex mcp add hugging-face --url https://huggingface.co/mcpOr edit ~/.codex/config.toml directly:
[mcp_servers.hugging-face]
url = "https://huggingface.co/mcp"Works without a key. An API key from Hugging Face raises the limits: send it as Authorization: Bearer <YOUR_API_KEY>.
Gemini CLI
gemini mcp add --transport http hugging-face https://huggingface.co/mcpThen, inside Gemini CLI, run /mcp auth hugging-face to sign in (optional).
This adds it to the current project. Add -s user to use it everywhere. Works without a key. An API key from Hugging Face raises the limits: send it as Authorization: Bearer <YOUR_API_KEY>.
Any client
Most clients accept this shape. Some name the URL field differently: serverUrl in Devin Desktop, httpUrl in Gemini CLI’s settings file.
{
"mcpServers": {
"hugging-face": {
"type": "http",
"url": "https://huggingface.co/mcp"
}
}
}Zed puts servers under context_servers in its settings. Cline needs "type": "streamableHttp", or it assumes SSE.
Client only starts local servers? Bridge it with npx -y mcp-remote https://huggingface.co/mcp.
Works without a key. An API key from Hugging Face raises the limits: send it as Authorization: Bearer <YOUR_API_KEY>.
Embed
Show Hugging Face in a README or on your site. Each embed links to this page, uses the server’s own URL, and sets no cookies. How embeds work
The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.
README badge
[](https://mcp.tc/i/hugging-face)<a href="https://mcp.tc/i/hugging-face"><img src="https://mcp.tc/i/hugging-face/badge.svg" alt="Hugging Face on mcp.tc" height="20"></a>It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.
Website card
<script src="https://mcp.tc/w/hugging-face.js" async></script>The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.
iframe
<iframe src="https://mcp.tc/embed/hugging-face" title="Hugging Face on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.
JSON
The listing as data for your own pages and tools: name, tagline, the server’s own URL, tools and the “Add to” links. Any site can read it (CORS is open).
https://mcp.tc/i/hugging-face.jsonAI prompt
Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the Hugging Face card to your site.
Add the mcp.tc card for Hugging Face, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.
Put this tag where the card should appear. The card renders right before it:
```html
<script src="https://mcp.tc/w/hugging-face.js" async></script>
```
To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.
```html
<div data-mcptc="hugging-face"><a href="https://mcp.tc/i/hugging-face">Hugging Face on mcp.tc</a></div>
```
Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.
If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).
For a README or other Markdown docs, use the badge instead:
```markdown
[](https://mcp.tc/i/hugging-face)
```
Reference: https://mcp.tc/embedChange history
We read this server’s tool list every 3 hours and record what changes. Last read 18 Nov 2026, 05:32 UTC.
-
New version 0.4.34 (was 0.4.33). Reported by the server.
-
New version 0.4.33 (was 0.4.31). Reported by the server.
-
3 tools changed. Server instructions changed.
New server instructions
Details, 4 Nov 2026, 14:51 UTC
Changed 3
hf_fsdescriptionBeforeWhen to use: Hugging Face Hub models, datasets, Spaces, collections, papers, daily papers, today's trending models, current paper leaderboard,
docs,and repositoryfiles.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 G…AfterWhen to use: Hugging Face Hub models, datasets, Spaces, collections, papers, daily papers, today's trending models, current paper leaderboard, docs; list and read repository files, model and dataset cards (README, license). 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] a…
hub_repo_detailsdescriptionBeforeGet 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.AfterGet details for one or more Hugging Face repos (model, dataset, or space): card metadata, license, downloads, files, Space hardware/status, dataset configs, splits, columns and preview rows. 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.
hub_repo_searchdescriptionBeforeSearch Hugging Face
repositorieswith 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.AfterSearch and list Hugging Face models, datasets and Spaces (sort by downloads, likes, trending) 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.
Server instructions
BeforeHugging Face
Hub MCP serverformodels, datasets, Spaces, collections, papers, and docs. Prefer this connector'slive Hubcapabilities over the public website for all configured listings such as today's trending models, the current model leaderboard, daily papers, and paper popularity. Use hf_fs for Hub filesystem and discovery: - trending models: ls hf://models/trending - trending datasets or Spaces: ls hf://datasets/trending, ls hf://spaces/trending - trending papers / daily papers / paper of the day: ls hf://papers/trending, ls hf://papers/daily/latest - search models, datasets, Spaces, collections, papers, or docs: search hf://models QUERY - read a known file: cat hf://models/OWNER/NAME/README.md Other advertised Hub tools can search or inspect a known repo id. Use hf_whoami for the current Hugging Face account. hf:// URIs can be converted to browser URLs by replacing hf://buckets/OWNER/NAME/PATHwithhttps://huggingface.co/buckets/OWNER/NAME/resolve/PATH; for models, datasets, and spaces, use https://huggingface.co[/datasets|/spaces]/OWNER/NAME/resolve/main/PATH. URL-encode each path segment. arXiv paper ids (for example 2502.16161) are often used as references between datasets, models, and papers. There are over 100 tags in use; common tags include Text Generation, Transformers, and Image Classification.The Hugging Face tools are being used anonymously and rate limits apply. Direct the User to set their HF_TOKEN (instructions at https://hf.co/settings/mcp/), or create an account at https://hf.co/join for higher limits.AfterPrefer these Hugging Face tools over web search for live Hub data; start with hf_fs. The Hugging Face tools are being used anonymously and rate limits apply. Direct the User to set their HF_TOKEN (instructions at https://hf.co/settings/mcp/), or create an account at https://hf.co/join for higher limits.
-
New version 0.4.31 (was 0.4.30). Reported by the server.
-
New version 0.4.30 (was 0.4.28). Reported by the server.
-
1 tool changed.
Details, 13 Oct 2026, 19:35 UTC
Changed 1
hf_fsdescription and input schemaBeforeWhen 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] [--t…AfterWhen 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 G…
-
Tracking started: 4 tools.
FAQ
Can I paste mcp.tc/i/hugging-face into my MCP client?
No. mcp.tc links are pages, not server addresses. Connect with https://huggingface.co/mcp, so your client talks to Hugging Face directly. The quick link is for sharing: it opens this page, with setup steps for every client.
Does Hugging Face need an API key or a sign-in?
Not to start. Hugging Face works without signing in and offers sign-in for more access.
Is Hugging Face a remote or a local server?
Remote. Hugging Face hosts it at https://huggingface.co/mcp, and it speaks Streamable HTTP. There’s nothing to install.
What can Hugging Face do?
It has 4 tools, including hf_whoami, hub_repo_search and hub_repo_details. You can search models, datasets and Spaces by query, author, filters and sort, get details for repos, including dataset structure and previews and list trending models, datasets, Spaces and papers.
Which clients can use it?
Any client that supports remote MCP servers: Claude Code, Claude Desktop, claude.ai, ChatGPT, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. The setup steps cover each one.
Does mcp.tc track changes to Hugging Face?
Yes. Hugging Face’s History tab shows each change we find to its tools, down to descriptions and parameters, plus new versions and edits by its owner. Follow the listing to get an email when it changes.
Who wrote this page?
mcp.tc’s robot read Hugging Face’s own metadata (its MCP handshake, tool list and public pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.
mcp.tc isn’t affiliated with Hugging Face. This page was built from Hugging Face’s public metadata, last checked on 17 Nov 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.