Does ChatGPT support the Hugging Face MCP server?

Yes. ChatGPT connects to the Hugging Face MCP server through its connector settings, pointed at your Metorial URL. You need a ChatGPT plan or workspace that allows custom MCP servers.

Do I need an API key to connect Hugging Face to ChatGPT?

No. You sign in to Hugging Face once through Metorial, and ChatGPT uses that connection. No API keys go into ChatGPT's settings.

Which Hugging Face tools can ChatGPT use?

All 29 Hugging Face tools your team allows, such as Control Space, Run Inference, Create Discussion. Admins can narrow that list per team.

Can I control which teammates use Hugging Face in ChatGPT?

Yes. Role-based access control decides who can use Hugging Face and which of its tools appear in ChatGPT, and every call is logged with the person's identity.

What if ChatGPT doesn't show Hugging Face tools?

Workspace policy controls it. On Enterprise and Edu, an admin grants the permission to create plugins with MCPs; ask them to enable it for you.

Connect Hugging Face to ChatGPT (MCP setup guide)

Ask ChatGPT to use the manage space secrets tool in Hugging Face
Ask ChatGPT to use the get discussion tool in Hugging Face
Ask ChatGPT to use the list discussions tool in Hugging Face
Ask ChatGPT to use the get user info tool in Hugging Face
Ask ChatGPT to use the create repository tool in Hugging Face

1. Enable Hugging Face in Metorial
In your Metorial portal, enable the Hugging Face MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
2. Add a custom MCP server
On ChatGPT web, open Plugins, select +, then Add custom MCP server.
3. Paste your Metorial MCP URL
Name it Metorial, paste your Magic MCP URL (<your-magic-mcp-url>), choose OAuth and accept the risk notice.
4. Create and install the plugin
Select Create as a plugin, install it and sign in to load Hugging Face tools.

Once Hugging Face is enabled in Metorial, teammates sign in with SSO and get the same connection in ChatGPT, with only the tools their role allows.

One link covers every app you approve. See how the MCP gateway handles access, roles and audit logs for the whole company.

Control Space: Control a Space's lifecycle: pause, restart, or change hardware.
Run Inference: Run generic inference on any Hugging Face model.
Create Discussion: Create a new discussion or pull request on a Hugging Face repository.
Search Datasets: Search for datasets on Hugging Face Hub.
Create Collection: Create a new collection to curate related models, datasets, and Spaces.
Manage Space Secrets: Add or delete secrets on a Space.
Get Discussion: Get detailed information about a specific discussion or pull request, including all comments and events.
List Discussions: List discussions and pull requests on a Hugging Face repository.
Get User Info: Get information about the authenticated user, including username, email, organizations, and account details.
Create Repository: Create a new model, dataset, or Space repository on Hugging Face Hub.
Delete Repository: Permanently delete a model, dataset, or Space repository from Hugging Face Hub.
Upload File: Upload or update a text file in a Hugging Face repository.
Remove Collection Item: Remove an item from a collection.
Update Repository Visibility: Change a repository's visibility between public and private.
List Repository Files: List files and directories in a Hugging Face repository at a given path and revision.
And 14 more on the Hugging Face MCP server page.

Type @ and pick the plugin. The selection applies to that message only, so @mention it again when a follow-up needs fresh Hugging Face data.
For write actions, ChatGPT may ask you to confirm first, depending on the app permissions and the action.
Once published for a workspace, ChatGPT keeps a snapshot of the tool list. When your team adds Hugging Face tools in Metorial, an admin refreshes the actions in Workspace settings before they appear.
You can use several apps in one prompt, for example read Hugging Face data and then create a ticket in another app.

Add custom MCP server is missing: Workspace policy controls it. On Enterprise and Edu, an admin grants the permission to create plugins with MCPs; ask them to enable it for you.
The plugin exists but no tools appear: Creating the plugin is not enough: install it from your plugins, then start a new conversation so ChatGPT loads its tools.
ChatGPT answers without using the tools: Pick the plugin with @ in the composer and name the action you want, for example "use Metorial to look up the latest ticket".

Based on the ChatGPT MCP documentation.

Frequently asked questions

Common questions about connecting Hugging Face to AI agents with Metorial.

Does ChatGPT support the Hugging Face MCP server?
Yes. ChatGPT connects to the Hugging Face MCP server through its connector settings, pointed at your Metorial URL. You need a ChatGPT plan or workspace that allows custom MCP servers.
Do I need an API key to connect Hugging Face to ChatGPT?
No. You sign in to Hugging Face once through Metorial, and ChatGPT uses that connection. No API keys go into ChatGPT's settings.
Which Hugging Face tools can ChatGPT use?
All 29 Hugging Face tools your team allows, such as Control Space, Run Inference, Create Discussion. Admins can narrow that list per team.
Can I control which teammates use Hugging Face in ChatGPT?
Yes. Role-based access control decides who can use Hugging Face and which of its tools appear in ChatGPT, and every call is logged with the person's identity.
What if ChatGPT doesn't show Hugging Face tools?
Workspace policy controls it. On Enterprise and Edu, an admin grants the permission to create plugins with MCPs; ask them to enable it for you.