Skip to content

Hugging Face MCP connector

The Hugging Face connector brings model, dataset and Space repositories into Elaichi, so Claude, ChatGPT, Cursor, Microsoft Copilot and the Elaichi Agent can search the Hub, read model cards and browse repository files as the signed-in person.

  • Connects over OAuth
  • Free 14-day trial
  • No credit card
ChatGPT Elaichi connected

Find Apache licensed text classification models with the most downloads

Working in Hugging Face with Elaichi

  • Hub repo search
  • Hf whoami
  • Hub repo details
Ask anything…
Governance / Audit log Last 24 hours
Hugging Face Hub repo details Emily Carter · ChatGPT · 9:41 AM Done
Hugging Face Hf whoami Emily Carter · ChatGPT · 9:41 AM Done
Hugging Face Hub repo search Emily Carter · ChatGPT · 9:41 AM Done
Hugging Face Hf fs Megan Brooks · Claude · 9:38 AM Done

How to connect Hugging Face to Claude, ChatGPT, Cursor or Microsoft Copilot

Step by step, for each AI app

Hugging Face MCP connector for Claude

  1. 1

    Open Customize, then Connectors.

  2. 2

    Press Add.

  3. 3

    Name it, paste the MCP server URL, then Continue.

    https://api.elaichi.ai/mcp
  4. 4

    Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

Hugging Face MCP connector for Claude Code

  1. 1

    In a terminal, run claude mcp add with the endpoint.

    https://api.elaichi.ai/mcp
  2. 2

    Start Claude Code and run /mcp.

  3. 3

    Pick elaichi, then sign in and approve in the browser.

Terminal

$ claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp

Use --scope project instead to share it with the repository through .mcp.json.

Hugging Face MCP connector for ChatGPT

  1. 1

    Open Plugins, then press the + button.

  2. 2

    Name it and paste the endpoint into Server URL.

    https://api.elaichi.ai/mcp
  3. 3

    Leave Authentication on OAuth, then tick the risk acknowledgement.

  4. 4

    Press Create, then sign in and approve.

Works on the web. The plugin directory lives at chatgpt.com/plugins.

Hugging Face MCP connector for Cursor

  1. 1

    Open ~/.cursor/mcp.json.

  2. 2

    Add the endpoint under mcpServers.

    https://api.elaichi.ai/mcp
  3. 3

    Reload Cursor, then sign in and approve.

~/.cursor/mcp.json

{
  "mcpServers": {
    "elaichi": {
      "url": "https://api.elaichi.ai/mcp"
    }
  }
}

Set up per machine, so repeat it on each computer you work from.

Hugging Face MCP connector for Microsoft Copilot

  1. 1

    In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.

  2. 2

    Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.

    https://api.elaichi.ai/mcp
  3. 3

    Create a new connection, sign in and approve, then press Add to agent.

  4. 4

    Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.

Server URL
https://api.elaichi.ai/mcp
Authentication
OAuth 2.0
Type
Dynamic discovery

Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.

Connect Hugging Face to any MCP client

  1. 1

    Add the endpoint as a remote MCP server.

    https://api.elaichi.ai/mcp
  2. 2

    Sign in and approve.

{
  "mcpServers": {
    "elaichi": {
      "url": "https://api.elaichi.ai/mcp"
    }
  }
}

The Elaichi Agent already has these tools, with nothing to set up.

What teams do with Hugging Face through Elaichi

Ask in plain English. Each person’s AI can do only what they’re allowed to, and every action it takes in Hugging Face is logged.

  • ML engineering

    Shortlist candidate models before a build

    Ask for the most downloaded text classification models on Hugging Face under an Apache license, then compare their model cards without opening a dozen tabs.

  • Data science

    Find a dataset that fits the task

    Search the Hub for datasets by task, language and size, then read the dataset card and look through the files before you commit to anything.

  • Research

    Read a model card without leaving the chat

    Pull the details of a specific repository, including its tags, license, downloads and recent updates, and have the agent summarize what matters for your paper or experiment.

  • Compliance

    Check a model's license before anyone ships it

    Have the agent confirm the license on each Hugging Face repository your teams are using and flag any that need a closer look.

  • Product

    Explain what a model does in plain language

    Ask for a non-technical summary of a model's card so a product review can move forward without waiting on an engineer.

  • Developer relations

    Keep track of your organization's public repositories

    List the models, datasets and Spaces published under your organization and read their cards to see which ones are out of date.

Try asking

  • “Find Apache licensed text classification models with the most downloads”
  • “Which French sentiment datasets have more than 10k downloads”
  • “List the files in our organization's latest model repository”

See all 4 Hugging Face tools →

What connecting Hugging Face gets you

6 screens from Elaichi, each doing one job for your Hugging Face account.

Elaichi Agent

Ask Elaichi to work across your apps.

Find Apache licensed text classification models with the most downloads

Which French sentiment datasets have more than 10k downloads

List the files in our organization's latest model repository

Also runs in Claude, ChatGPT, Cursor or Microsoft Copilot

The agent

Ask about models and get live answers.

Search models, datasets and Spaces on Hugging Face in plain language, as yourself.

ElaichiAI apps
Claude ChatGPT Cursor Microsoft Copilot

Copy the endpoint

https://api.elaichi.ai/mcp
Client Connected by Status Last used
Claude
E

Emily Carter

• Connected 4 minutes ago
Cursor
M

Megan Brooks

• Connected 2 hours ago
ChatGPT
R

Ryan Hayes

• Connected Yesterday

AI apps

One endpoint puts Hugging Face in every client.

Claude, ChatGPT, Cursor and Microsoft Copilot connect once over OAuth, with no SDK and no shared token.

ElaichiTools
Tool Action Description
Hf whoami Action 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 Search 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.
Hub repo details Action 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…
Hf fs Action 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"]}]}…

Tool catalog

4 Hugging Face tools, ready with no code.

Search the Hub, read repository details, browse files and check the signed-in account.

ElaichiToolboxes
Name Source template Tools Created

Research toolbox

Hugging Face · model discovery and cards

Hugging Face starter 18 Mar 4, 2026

Data science toolbox

Hugging Face · datasets and files

— 9 Mar 2, 2026

ML engineering toolbox

Hugging Face · model repositories and weights

— 24 Feb 27, 2026

Compliance toolbox

Hugging Face · licenses and provenance

Hugging Face starter 6 Feb 19, 2026

Product toolbox

Hugging Face · model summaries for reviews

— 31 Jan 30, 2026

Developer relations toolbox

Hugging Face · the organization's public repositories

— 12 Jan 22, 2026

Toolboxes

Every team gets its own Hugging Face toolbox.

Research, data science and compliance each see the tools their work needs.

ElaichiConnections
Connection Scope Status Access
HU

Hugging Face (Research)

Connected by Emily Carter

Personal • Active 1 team · 6 members
HU

Hugging Face (Data science)

Connected by Jake Morgan

Organization • Active 3 teams · 24 members
HU

Hugging Face (ML platform)

Connected by Megan Brooks

Organization • Active 2 teams · 11 members
HU

Hugging Face (Compliance)

Connected by Tyler Reed

Personal • Needs re-auth 1 team · 3 members
HU

Hugging Face (Product)

Connected by Ryan Hayes

Personal • Active Not shared
HU

Hugging Face (DevRel)

Connected by Ashley Parker

Personal • Active 2 teams · 9 members

Shared connections

Teammates work through one connection, never a token.

One person connects Hugging Face, shares with teams, and nobody else handles a credential.

ElaichiAudit log
When Who What happened Type

2 minutes ago

Mar 6, 2026, 3:10 PM

E

Emily Carter

[email protected]

Restriction Created Access

8 minutes ago

Mar 6, 2026, 3:04 PM

J

Jake Morgan

[email protected]

Restriction Updated Access

14 minutes ago

Mar 6, 2026, 2:58 PM

M

Megan Brooks

[email protected]

Role Assigned Access

20 minutes ago

Mar 6, 2026, 2:52 PM

T

Tyler Reed

[email protected]

Hugging Face Users Updated MCP

26 minutes ago

Mar 6, 2026, 2:46 PM

R

Ryan Hayes

[email protected]

Hugging Face Models Created MCP

32 minutes ago

Mar 6, 2026, 2:40 PM

A

Ashley Parker

[email protected]

Hugging Face Models List Toolbox

Audit log

Every Hugging Face call is on the record.

When, who, what happened and which repository, written to an append-only log.

From answering questions to doing the work

A trigger starts the work, inside the same permissions and the same audit log as everything else. Workflows, collections and live dashboards come with the Black plan.

Hugging Face digest

Run 418 · started 2 minutes ago · on behalf of Emily Carter

  1. ✓

    Schedule

    Every weekday at 8:00 AM

    0.2s
  2. ✓

    Fetch models

    Hugging Face

    1.4s
  3. ✓

    Group by owner

    Transform

    0.1s
  4. ✓

    Draft the digest

    Agent step

    Ran with 4 tools, returned a structured summary

    6.2s
  5. Approve the digest

    Needs approval

    Assigned to Jake Morgan

    Approve
  6. Post the digest

    Hugging Face

    Queued

Workflows

A schedule starts the work, a person approves.

New Hugging Face repositories are fetched, grouped, drafted into a digest, approved and posted back.

Hugging Face health

Refreshed 4 minutes ago · every 15 minutes · from the models collection

Live

Models

1,284 ↓ 12%

Datasets

96 ↓ 8%

Needs attention

3 ↑ 2

Updated this week

412 ↑ 9%

Models created

Last 14 days

By team

Share of activity

Research 34%

Data science 27%

ML platform 21%

Compliance 18%

Collections and dashboards

Hugging Face health, computed without a model.

Four metrics, 14 days of repositories created and a team breakdown, refreshed on schedule.

Why connect Hugging Face's MCP server through Elaichi

Hugging Face builds and runs this MCP server. Elaichi sits in front of it, so Hugging Face's tools follow the same sign-in, access rules and audit log as every other connector your organization uses. Calls an AI client makes to Hugging Face's server directly, outside Elaichi, get none of this.

  • One address for every AI client

    Claude, ChatGPT, Cursor and Microsoft Copilot reach Hugging Face's tools at the same Elaichi address as every other connected app. Nobody adds Hugging Face's server to each client one by one.

  • Each person signs in as themselves

    Each person signs in to Elaichi as themselves. Members connect with their own Hugging Face sign-in, and a connection someone shares runs on its owner's account. The credential stays in Elaichi's separate credential service, and the AI client holds only its Elaichi sign-in.

  • Rules checked before a call leaves

    Restrictions on a role or a person, for the whole connector or a single tool, are checked before a call reaches Hugging Face's server. By default, a tool Hugging Face does not mark read-only or non-destructive counts as destructive, and over MCP it still runs under the "Use your connected apps" consent.

  • One audit log for every app

    Each call that runs is recorded with the person, the tool, the connection and the AI client that made it, in the same audit log as every other app.

  • Tool issues go to Hugging Face

    Hugging Face builds and runs these tools, and Elaichi staff do not curate them, so a report about how a tool behaves goes to the Hugging Face team.

    huggingface.co/support

Why run a vendor's MCP server through Elaichi →

For IT and engineering

Elaichi vs Zapier MCP vs Composio for Hugging Face

All three can connect Hugging Face to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

Elaichi compared with Zapier MCP and Composio for Hugging Face, by what to check
What to check Elaichi Zapier MCP Composio
Where the AI connects One address for the whole organization. https://api.elaichi.ai/mcp A server per member, created at sign-in. An MCP endpoint per team, or an SDK.
Control over Hugging Face tools Allow or restrict single Hugging Face tools, per role or user. App and action restrictions on the account. Role permissions, down to the action.
Record of calls One audit entry per Hugging Face call. A History tab of tool calls. A log of every tool call.
Single sign-on SAML or OIDC, plus SCIM, on Gold. SAML on Enterprise. SAML and OIDC on Enterprise.
Price Free for one person; $15 per user per month on Gold. 2 tasks per successful call. Billed per tool call.

Sources: Zapier MCP docs, security, usage; Composio docs, gateway, enterprise, pricing. Checked September 2026.

Longer take: Zapier MCP alternative and when you don't need an MCP gateway.

Hugging Face tools for your AI agents

4 tools are ready to call through Elaichi's MCP endpoint the moment you connect Hugging Face, governed by the same roles, restrictions, and audit log as everything else in Elaichi. Hugging Face builds and runs these tools.

Questions, answered

How do I connect Hugging Face to Claude?

Connect Hugging Face in Elaichi first: pick it from the catalog and sign in with your Hugging Face account over OAuth, approving the access it asks for. There is no OAuth application to register and no client ID or secret to generate. Then in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Claude signs you in through Elaichi and Hugging Face is available in your next conversation.

Does Hugging Face work with ChatGPT and Cursor as well as Claude?

Yes. Once Hugging Face is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any other MCP client and the Elaichi Agent. You connect Hugging Face once and every client you use picks it up.

What can an AI agent actually do with my Hugging Face data?

With Hugging Face connected, an agent can search the Hub for models, datasets and Spaces, read a repository's card, license, tags and download counts, browse the files inside a repository, and confirm which Hugging Face account it is working as. Short, concrete asks work best, such as the license of a named model or the most downloaded datasets for a task, rather than long multi-part sentences.

Does connecting Hugging Face give the AI access to all my repositories and organizations?

No. Every call to Hugging Face runs as the person who signed in, so the agent sees only the public repositories and the private repositories and organizations that person can already open on Hugging Face. Elaichi can narrow that further with roles and restrictions, but it can never widen what Hugging Face itself allows.

Can my team share one Hugging Face connection?

Yes. One person connects Hugging Face in Elaichi and shares the connection with a team, and nobody else ever handles a token. Each teammate still signs in to Elaichi as themselves, so the audit log names the person who searched the Hub or read a repository, not a shared account.

Can I stop an agent from changing things in Hugging Face?

Yes. Restrictions in Elaichi apply per action on the Hugging Face connector, so you can leave searching and reading open while closing off anything you do not want an agent to touch. A restricted action still appears in Elaichi's tool search, flagged as restricted, but Claude, ChatGPT, Cursor or Microsoft Copilot cannot run it, whatever the prompt says.

What happens to a Hugging Face connection when someone leaves?

Offboarding a person in Elaichi ends their access to Hugging Face through every client at once. A Hugging Face connection shared with a team keeps working for everyone else, and if you disconnect Hugging Face in Elaichi it disappears from Claude, ChatGPT, Cursor, Microsoft Copilot and the Elaichi Agent in one step.

Does the Hugging Face MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Hugging Face is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

Is Elaichi an alternative to Zapier MCP for Hugging Face?

Yes. Both let Claude, ChatGPT or Cursor use Hugging Face. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Hugging Face call.

How is Elaichi different from Composio for Hugging Face?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Hugging Face: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

Put Hugging Face in front of your team

14 days of Black, no credit card. Connect it once and pick what each team can call.

When the trial ends, nothing is deleted. You move to the free Personal plan, and connections, roles and the audit log stay where they are.

Add one link to your AI app

The same link for everyone on your team.

https://api.elaichi.ai/mcp
  • ChatGPT
  • Claude
  • Cursor
  • Microsoft Copilot