HuggingFace

Connect AI agents to HuggingFace for ML model hosting and inference

Prerequisites Before you begin, create an account and get your API Key.

Getting started

Connect to HuggingFace to access ML models, manage datasets, and run inference through AI agents.

API

1. Install the SDKs (optional)

   pip

   pip install klavis
   
2. Create a Strata MCP Server with HuggingFace

   Python

   from klavis import Klavis
   from klavis.types import McpServerName
   
   klavis_client = Klavis(api_key="YOUR_API_KEY")
   
   response = klavis_client.mcp_server.create_strata_server(
       servers=[McpServerName.HUGGINGFACE],
       user_id="user123"
   )
   

   userId specifies whose connected accounts and data you are accessing in Klavis. It should be a unique id for yourself, your team, or your organization.

   API Reference

   Full Strata API endpoints

3. Authenticate

   Python

   import webbrowser
   
   # Open OAuth authorization page
   webbrowser.open(response.oauth_urls[McpServerName.HUGGINGFACE])
   

   Your HuggingFace MCP Server is ready! Once authentication is complete, you can use your MCP server URL with any MCP-compatible client.

UI

1. Open Dashboard

   Go to your Dashboard.

2. Choose HuggingFace

   Select HuggingFace from the list of available integrations.

3. Authenticate

   Complete the OAuth flow to connect your HuggingFace account.

4. Use in your app

   Copy the MCP endpoint URL and add it to your MCP-supported client (Claude Desktop, Cursor, VS Code, etc.).

Available Tools

With our progressive discovery approach, Klavis System is capable of enabling all tools for HuggingFace. Please use the get_tools API for more details. If you find any tool that is missing, please reach out to [e-mail].

Next Steps

White-label Authentication

Customize OAuth flows with your own branding

AI Platform Integrations

Integrate Klavis MCP Servers with leading AI platforms

Integrations

Explore available MCP servers

API Reference

REST endpoints and schemas