Frequently Asked Questions (FAQ) about UBOS Asset Marketplace MCP Server
Q: What is MCP Server?
A: MCP (Model Context Protocol) Server acts as a bridge, allowing AI models to access and interact with external data sources and tools. In the context of the UBOS Asset Marketplace, it allows seamless connection between Hugging Face Spaces and Claude Desktop.
Q: How do I install the MCP Server?
A: The MCP Server is installed as an NPM package. Use the command npm install -g @llmindset/mcp-hfspsace.
Q: How do I configure the MCP Server for Claude Desktop?
A: Add the server configuration to your claude_desktop_config.json file. This file is located in ~/Library/Application Support/Claude/ on macOS and %APPDATA%/Claude/ on Windows. Include the command, arguments, and desired Hugging Face Spaces.
Q: What Hugging Face Spaces are recommended?
A: Recommended spaces include shuttleai/shuttle-3.1-aesthetic and black-forest-labs/FLUX.1-schnell for image generation, Qwen/Qwen2.5-72B-Instruct for chat, hf-audio/whisper-large-v3-turbo for speech-to-text, and microsoft/OmniParser for vision tasks.
Q: How do I use private Hugging Face Spaces with the MCP Server?
A: Supply your Hugging Face token via the --hf-token=hf_... argument or the HF_TOKEN environment variable.
Q: What is Claude Desktop Mode?
A: In Claude Desktop Mode, images are returned in tool responses, and other files are saved in the working folder. The file path is then returned as a message, providing the best experience when using Claude Desktop as the client.
Q: Can I disable Claude Desktop Mode?
A: Yes, you can disable it with the option --desktop-mode=false or the environment variable CLAUDE_DESKTOP_MODE=false. In this case, content is returned as an embedded Base64 encoded resource.
Q: How do I specify a working directory?
A: Specify the --work-dir=/your_directory argument or set the MCP_HF_WORK_DIR environment variable.
Q: How does the MCP Server integrate with the UBOS platform?
A: The MCP Server seamlessly integrates with the UBOS full-stack AI Agent Development Platform, enabling orchestration of AI Agents, connection with enterprise data, building custom AI Agents, and developing Multi-Agent Systems.
Q: What if I encounter issues with Claude Desktop timing out?
A: Claude Desktop has a hard timeout value of 60s. If you encounter timeouts with large/heavy jobs, check the WORK_DIR for results, as the MCP Server will still capture and save the result if it was produced before the timeout.
Hugging Face Spaces Connector
Project Details
- xiyuefox/mcp-hfspace
- @llmindset/mcp-hfspace
- MIT License
- Last Updated: 3/10/2025
Recomended MCP Servers
Java implementation of MCP Server for Craw4ai
Pull pagespeed data using this MCP server.
This is a personal project to test Claude AI's ability to self-write an MCP Server code for its...
An implementation of the Model Context Protocol for the World Bank open data API
Stock market data provider for Claude Desktop using MCP
Magic admin Python SDK makes it easy to leverage Decentralized ID tokens to protect routes and restricted resources...
A simple MCP ODBC server using FastAPI, ODBC and SQLAlchemy.
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities,...
A Model Context Protocol (MCP) server that enables AI models to interact with the Zerodha trading platform. This...





