Arthur MCPArthur MCP
Dashboard
How it worksFeaturesDocsEarly accessGitHubDashboard

How to integrate Hugging Face using MCP

Open AI models and inference API. This guide creates an MCP server from Arthur's Hugging Face template — tools preconfigured against https://api-inference.huggingface.co/models — and finishes by sharing the server's MCP swagger documentation.

Steps

  1. Open the Secrets vault and create a secret named HUGGINGFACE_API_KEY holding your access token. Create a User Access Token at huggingface.co/settings/tokens with "Inference" permissions.

    Open the Secrets vault to store the Hugging Face credential before using the template

    Start the New secret wizard

    Name the secret HUGGINGFACEAPIKEY — servers reference it by this name

  2. Go to the REST API Templates gallery and search for Hugging Face.

    Record what the credential is for so it stays recognizable

    Continue to the protected value step

  3. Click Use template on the Hugging Face card to open the server-creation dialog.

    Enter the credential value — a demo value here; use your real key when adopting the integration

    Review the generated secret reference syntax

  4. Review the server name and select HUGGINGFACE_API_KEY in the credential field — the dialog only accepts vault secrets, and it lists every tool that will be created.

    Store the HUGGINGFACEAPIKEY secret in the vault

    Open the REST API template gallery

    Search the gallery for the Hugging Face integration

  5. Click Create server. Arthur creates the server, applies the authentication, and generates all the tools.

    Open the Hugging Face template with its preconfigured tools

    Name the server after the integration it provides

    Pick the HUGGINGFACEAPIKEY secret from the vault suggestions

    Select the stored credential

    Create the Hugging Face server with its preconfigured tools

  6. Open the server's Tools tab to review the generated tools.

    Review the tools generated from the Hugging Face template

  7. Open the server's Connect section and click Share the MCP swagger documentation — Arthur generates the public documentation link and QR code for this server.

    Open the server's Connect section, where the MCP endpoint and its documentation live

    Open the MCP swagger documentation share panel

    Show the generated swagger documentation link and QR code for this server

Confirm it worked

The server appears with 3 preconfigured tool(s): text_generation, text_classification, image_to_text. The Connect section offers the MCP swagger documentation — a shareable page with setup instructions for any AI client.

Good to know

  • Run inference on thousands of open-source AI models — text generation, classification, image generation, audio, and more — via the Hugging Face Inference API.
  • This integration requires a credential (bearer). Get one at https://huggingface.co/join.
  • Official API documentation: https://huggingface.co/docs/api-inference
  • Editing a tool later never changes the template — templates are starting points, and the server is fully yours after creation.

Related

Tutorial video