MewCP LogoAStheTech
MCPs
Use Cases

Use cases by category

Productivity & InboxInbox, calendar, and daily flowEngineering & DevOpsShip, debug, and run on-callSales & CRMPipeline, outreach, and dealsMarketing & GrowthCampaigns, SEO, and growthSupport & SuccessTriage tickets, keep customers happyFinance & OpsClose, reconcile, and expensesCreative & ContentGenerate assets and contentPeople & HiringHiring, onboarding, and HRResearch & DataSynthesize data and insights
See all use cases
Resources
BlogsProduct updates and storiesArticlesIntegration guides and code examples
PricingDocsSign in
MewCP Logo

Infrastructure You Can Trust for Agentic Products

X

Categories

  • Productivity & Docs
  • Developer Tools
  • CRM & Sales
  • Finance & Commerce
  • Data & Analytics
  • Marketing & SEO
  • Search & Web
  • Communication
  • View All Servers →

Resources

  • Blog
  • Docs
  • Privacy Policy
  • Terms of Service

Blogs

  • View All Blogs →

Articles

  • View All Articles →
Browse Servers|Pricing|Contact

Browse by Category

Productivity & Docs

  • Gmail
  • Google Drive
  • YouTube
  • Google Calendar
  • Google People
  • Google Classroom
  • Notion
  • ClickUp
  • Figma
  • Google Tasks
  • Cal
  • Monday
  • Luma
  • Notion MCP
  • Mem MCP
  • Linear MCP
  • Calendly MCP
  • Consensus MCP
  • Craft MCP
  • Close MCP
+ 23 more
  • Dice MCP
  • Lumin PDF MCP
  • Develop21 MCP
  • Granola MCP
  • Lucid MCP
  • Mermaid Chart MCP
  • Fireflies MCP
  • ClickUp MCP
  • Miro MCP
  • Llamaindex MCP
  • Otter MCP
  • Mobbin MCP
  • Descript MCP
  • ToDoist MCP
  • SlidesGPT MCP
  • AgileHero MCP
  • JobYap MCP
  • AccountHub MCP
  • Slicktrip MCP
  • Gemina MCP
  • QrVerloz
  • Tempreon MCP
  • HyperFrames MCP

Developer Tools

  • Gemini
  • Veo
  • ClickUp
  • Firecrawl
  • Vercel
  • Apify
  • Github
  • Chef
  • Scientific Calculator
  • Figma
  • HTTP
  • Perplexity
  • Apify MCP
  • Hugging Face Hub MCP
  • Buildkite MCP
  • Cloudflare MCP
  • Context7 MCP
  • Ahrefs MCP
  • Sentry MCP
  • Brevo Docs MCP
+ 53 more
  • X Docs MCP
  • Jev
  • Linear MCP
  • Calendly MCP
  • Craft MCP
  • DeepWiki MCP
  • Inspo MCP
  • Kernel MCP
  • Malwarebytes MCP
  • Mermaid Chart MCP
  • Supabase MCP
  • Microsoft Learn MCP
  • Webflow MCP
  • Scalar Docs MCP
  • Oneuptime MCP
  • Redocly MCP
  • Reducto Docs MCP
  • Llamaindex Docs MCP
  • B12 MCP
  • Lucid Docs MCP
  • Airwallex Docs MCP
  • Langfuse Docs MCP
  • Glen Docs MCP
  • AgentMail
  • Gogs Docs MCP
  • Netlify MCP
  • Neon MCP
  • Minlify Admin MCP
  • Mintlify Index MCP
  • Fern Docs MCP
  • Greptile MCP
  • Statssif Docs MCP
  • Scorecard MCP
  • Railway MCP
  • Inkbox AI
  • Stele MCP
  • LastPing MCP
  • ConsentStack
  • Iubenda MCP
  • BSV.CX MCP
  • Agent Traffic Lab MCP
  • Nippy MCP
  • Just Domain MCP
  • Grafana Cloud MCP
  • HotAPI Docs
  • Endoflife.ai MCP
  • ElevenLabs MCP
  • Laso Docs MCP
  • OpenRouter MCP
  • Replit MCP
  • Tripadvisor Docs MCP
  • GitLab MCP
  • Mailchimp Docs MCP

CRM & Sales

  • Google People
  • OneSignal MCP
  • Brevo Docs MCP
  • Brevo
  • Brevo MCP
  • Carbon Voice MCP
  • Clay MCP
  • Close MCP
  • Attio MCP
  • Clarify MCP
  • Hunter.io
  • Plain MCP
  • Modem MCP
  • Whats MCP

Finance & Commerce

  • Kite
  • Razorpay
  • Polymarket
  • Stripe
  • Binance
  • Upstox
  • Aiwyn MCP
  • Era-Context-MCP
  • Granted MCP
  • XDC AI MCP
  • Agentery MCP
  • Agent Embassy
  • Quick Commerce MCP
  • Longbridge MCP
  • Mercury MCP
  • Blockscout MCP
  • Octagon AI MCP
  • Stripe MCP
  • Taskrabbit MCP
  • SeatGeek MCP
+ 16 more
  • Clarity AI MCP
  • Beyond Payday MCP
  • DeFade MCP
  • MobileMRR MCP
  • SecondAppraisal MCP
  • Brek MCP
  • Coinversa Pulse MCp
  • Supermetrics Marketing Analytics MCP
  • DeepLedger MCP
  • Laso MCP
  • Laso Docs MCP
  • Razorpay MCP
  • Kiwi MCP
  • lastminute mcp
  • Coinfuty MCP
  • Pyth MCP

Data & Analytics

  • Apify MCP
  • Cloudflare MCP
  • Ahrefs MCP
  • Candid MCP
  • Consensus MCP
  • Contentsquare MCP
  • Era-Context-MCP
  • Instinct MCP
  • legal Data Hunter MCP
  • Marcopolo MCP
  • Mixpanel MCP
  • MOSPI MCP
  • Hex MCP
  • OpenRevenue MCP
  • Statsig MCP
  • Synthesize Bio MCP
  • PostHog MCP
  • PopHIVE MCP
  • Fuse Health MCP
  • Cliometry MCP
+ 5 more
  • AccuWeather MCP
  • ChEMBL MCP
  • ClinicalTrials.gov MCP
  • Staats MCP
  • NPI Registry MCP

Marketing & SEO

  • YouTube
  • Google Business
  • Mailchimp
  • Google Search Console
  • OneSignal MCP
  • Cloudflare MCP
  • Brevo Docs MCP
  • Brevo
  • Brevo MCP
  • AirOps MCP
  • Clay MCP
  • Contentsquare MCP
  • Reelsmith MCP
  • GoDaddy MCP
  • Metricool MCP
  • Webflow MCP
  • Windsor MCP
  • Commonroom MCP
  • B12 MCP
  • Hunter.io
+ 14 more
  • Get MCP Ads
  • Minlify Admin MCP
  • Zernio MCP
  • Affiliatespy MCP
  • VarynForge
  • ListingGood MCP
  • North Noir MCP
  • Supermetrics Marketing Analytics MCP
  • NitroSend MCP
  • Spicy MCP
  • Cromanion MCP
  • Manifold MCP
  • Cloro MCP
  • Agency AI MCP

Search & Web

  • Web Scrapper
  • Firecrawl
  • Apify
  • Perplexity
  • Context.dev
  • Exa
  • Brave Search
  • Apify MCP
  • Ahrefs MCP
  • DeepWiki MCP
  • Dice MCP
  • GoDaddy MCP
  • Granted MCP
  • Microsoft Learn MCP
  • Viator MCp
  • Scholargateway MCP
  • Parallel MCP
  • Mintlify Index MCP
  • OpenWeather MCP
  • Simplescraper MCP
+ 8 more
  • SearchApi MCP
  • PubMed MCP
  • YouTube Transcript AI MCP
  • AccuWeather MCP
  • bioRxiv MCP
  • HEY Research Lab MCP
  • CourtListener MCP
  • Elicit MCP

Communication

  • Gmail
  • Google Meet
  • Google Calendar
  • Mailchimp
  • WhatsApp
  • Slack
  • OneSignal MCP
  • Brevo Docs MCP
  • Carbon Voice MCP
  • Hunter.io
  • Outlook
  • Nylas MCP
  • Resend MCP
  • Read AI MCP
  • Whats MCP
  • Inkbox AI
  • QrVerloz
  • ElevenLabs MCP
  • Fathom MCP

© 2026 MewCP. All rights reserved.

  1. Home
  2. MCPs
  3. Hugging Face Hub MCP
Hugging Face Hub MCP

Hugging Face Hub MCP Integration for AI Agents

AI model hub for machine learning. Discover models, explore datasets, and access model documentation and capabilities.

v0.4.1912 toolsOAuth
Open in ChatGPTChatGPT
Open in ClaudeClaude
Playground
VS CodeVS Code
Connected to Hugging Face Hub MCP via MewCP.

Encrypted at rest, isolated from the model

Resolved from an AES-256-GCM vault at the moment of the call and attached to the request — the model never sees the secrets.

Try asking

Everything Hugging Face Hub MCP can do

Tools12

hf_whoami

read

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

hub_repo_search

read

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.

create_repo

write

Create a Hugging Face model, dataset, Space, or bucket repository using an hf:// destination URI. Set source_uri to duplicate an existing model, dataset, or Space server-side.

hub_repo_details

read

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.

hf_fs

read

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 resource root or owner scope to discover resources; use find for file discovery within a repository or cat for a known text file. Paper and documentation search require QUERY. --tag (repeatable) and --kind are supported only on exactly hf://spaces, not owner scopes or other roots. The only valid --kind value is mcp, which selects MCP Spaces. Use ls hf://models/trending, hf://datasets/trending, hf://spaces/trending, or hf://papers/trending for trending listings. hf://papers/ID is a paper directory, not paper text. Use cat hf://papers/ID/paper.md for paper text and cat hf://papers/ID/metadata.json for metadata. No preliminary listing is needed for these known paths. Use ls hf://papers/ID to discover other resources. Omit --limit, --sort, and --type unless the request requires them. Limits and path-specific behavior are documented at hf://README.md. Issue one hf_fs call.

hf_fs_write

destructive

Write or remove files in Hugging Face repositories and buckets. Grammar; each token below is one args array element: put URI [--base64] [(-m|--message) MESSAGE] [--description DESCRIPTION] [--branch BRANCH] [--create-pr] [--parent-commit SHA] rm URI [(-m|--message) MESSAGE] [--description DESCRIPTION] [--branch BRANCH] [--create-pr] [--parent-commit SHA] URI must be an hf://models|datasets|spaces|buckets/OWNER/NAME/PATH file URI. For put, provide file data in the separate content field. Content is UTF-8 text unless --base64 is present. Use --create-pr to propose a change when direct repository writes are unavailable or undesirable. Branches, pull requests, descriptions, and parent commits are not supported for buckets. A URI '@revision' and --branch are equivalent; do not specify conflicting values. --parent-commit must be a 40-character Git commit SHA and prevents overwriting concurrent changes. No pipes, redirects, shell expansion, or multiple commands.

hf_jobs

destructive

Remote compute for Hugging Face workflows. Run Python/UV or Docker jobs to deeply analyze Hub datasets, repos, traces, models, and large files; compute trends/statistics; run batch inference/evaluation; or perform long-running work with installed libraries. Use for dataset/repo analysis prompts when local chat inspection is insufficient. Includes submit, logs, inspect, cancel, schedule, and volume mounting. Minimal run: {"operation":"run","args":{"image":"python:3.12","command":["python","-c","print(123)"]}}. Command arrays are literal argv; strings tokenize quotes and escaping, not shell execution. For pipes, chaining, redirections, or variable expansion, explicitly use ["/bin/sh", "-lc", "..."] only if the image provides that shell. Help: {"operation":"run","args":{"help":true}}; full usage: {}. Follow up with logs or inspect using args: {"job_id":"<returned job ID>"}.

hf_sandbox

destructive

Create and manage Hugging Face Sandboxes. Grammar; each token below is one args array element: create [--name NAME] [--image IMAGE] [--flavor FLAVOR] [--timeout DURATION] [--namespace NAMESPACE] [--resource-group-id ID] [--forward-hf-token] [--volume SPEC]... [--bucket OWNER/NAME] [--bucket-mode ro|rw] [--bucket-mount-path PATH] status HANDLE terminate HANDLE ps HANDLE kill HANDLE PROCESS_ID HANDLE is returned by create. Volume SPEC is hf://[models|datasets|spaces|buckets]/OWNER/NAME[/PATH]:/MOUNT_PATH[:ro|:rw]. No pipes, redirects, shell expansion, or multiple commands.

hf_sandbox_exec

destructive

Run a shell command inside a Hugging Face Sandbox. Grammar; each token below is one args array element: exec HANDLE SHELL_COMMAND [--workdir PATH] [--stdin TEXT] [--timeout SECONDS] [--env NAME=VALUE]... [--detach] [--tag TAG] SHELL_COMMAND is one string token and runs via /bin/sh -lc. Foreground timeout defaults to 30 seconds and may not exceed 55. Detached commands have no timeout unless set. Redirect detached output to a file.

hf_sandbox_fs

destructive

Read, write and manage files inside a Hugging Face Sandbox. Grammar; each token below is one args array element: ls HANDLE PATH cat HANDLE PATH [--offset N] [--max-bytes N] stat HANDLE PATH write HANDLE PATH (--text TEXT|--base64 BASE64) rm HANDLE PATH [(-r|-R|--recursive)] mkdir HANDLE PATH PATH is an absolute path inside the sandbox. cat defaults to 20000 bytes and allows at most 100000.

dynamic_space

destructive

Perform Tasks with Hugging Face Spaces. Use "discover" to view available Tasks. Examples are Image Generation/Editing, Background Removal, Text to Speech, OCR and many more. Call with no arguments for full usage instructions.

gr1_z_image_turbo_generate

destructive

Generate an image using the Z-Image model based on the provided prompt and settings. This function is triggered when the user clicks the "Generate" button. It processes the input prompt (optionally enhancing it), configures generation parameters, and produces an image using the Z-Image diffusion transformer pipeline. Returns: tuple: (gallery_images, seed_str, seed_int), - seed_str: String representation of the seed used for generation, - seed_int: Integer representation of the seed used for generation (from mcp-tools/Z-Image-Turbo)

Connect Hugging Face Hub MCP to your agent

One endpoint, the same key, whichever client you use.

Apps

SDKs

Claude Desktop

Claude Desktop

~/Library/Application Support/Claude/claude_desktop_config.json (Mac) · %APPDATA%\Claude\claude_desktop_config.json (Windows)

JSON
{
  "mcpServers": {
    "mewcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://gateway.mewcp.com/personal/mcp",
        "--header",
        "Authorization:${AUTH_HEADER}"
      ],
      "env": {
        "AUTH_HEADER": "Bearer API_KEY"
      }
    }
  }
}

Replace API_KEY with your own key.

Already have an "mcpServers" section in your config? Just add the server entry inside it.

  1. 01Open Claude Desktop → Settings → Developer → "Edit Config"
  2. 02Paste the snippet inside the outer { } of the config file (merge with your existing "mcpServers" section if you have one)
  3. 03Save the file, then quit Claude Desktop completely and reopen it
  4. 04Start a new conversation — your tool will be available

One endpoint. Every service.

VS CodeAny agent
One Gateway

Firecrawl

API Key

Github

OAuth

HTTP

No auth

Hugging Face Hub MCP

OAuth

Discovery, routing, credentials, tool scoping and execution logs all happen at the gateway→connections stay ACTIVE with no work from you

Separate connections░░░░░░░░░░░░░░░░░░░░░░░░░░░░83 tool definitions ~19k tokensWith MewCP░░░░░░░░░░░░░░░░░░░░░░░░░░░░4 meta-tools ~3.1k tokens

Built for AI agents

Hugging Face Hub MCP runs through a gateway that holds the credentials, scopes the access and records every call.

Managed authentication

  • OAuth to Hugging Face Hub MCP handled end to end, with tokens refreshed before they expire.
  • One credential per end user, not one shared key across your users.
  • Reconnect an account without touching your agent's config.

Credentials stay out of context

  • Hugging Face Hub MCP credentials are resolved at the gateway and attached to the outbound call.
  • The agent sees tool results, never a token.
  • Revoke an account and the next call stops working — no redeploy.

Scoped access, fully logged

  • Choose exactly which Hugging Face Hub MCP tools an agent is allowed to call.
  • Every call is logged with its outcome, latency and which account it ran as.
  • Catalog changes are reviewed before they ship, so tool descriptions cannot shift under you.

One endpoint for every server

  • Reach Hugging Face Hub MCP through the same MCP endpoint as the rest of your toolset.
  • Tools are discovered on demand, so 12 tools do not fill the context window.
  • Stateless: no sessions to keep alive and no reconnect logic.

Ready to connect Hugging Face Hub MCP?

Managed auth, hosted MCP servers, and every Hugging Face Hub MCP tool your agent needs.

Free to start.