Frequently Asked Questions (FAQ)

Q: What is the Model Context Protocol (MCP)? A: MCP is an open protocol standardizing how applications provide context to Large Language Models (LLMs), enabling AI models to access and interact with external data sources and tools.

Q: What is the UBOS MCP Server? A: The UBOS MCP Server (Extended Jupyter Model Context Protocol Server) is a tool available on the UBOS Asset Marketplace that connects AI models (like Claude) to Jupyter notebooks, allowing for rich, interactive communication and automation.

Q: What are the key features of the UBOS MCP Server? A: Key features include seamless integration with JupyterLab, cell management, execution control, file system access, kernel introspection, package management, notebook state manipulation, and enhanced collaboration capabilities.

Q: What are the requirements for using the UBOS MCP Server? A: Requirements include Python (>= 3.10 recommended), JupyterLab, the jupyter_collaboration==2.0.1 extension, datalayer_pycrdt, Docker, Pillow, and an MCP Client (e.g., Claude Desktop).

Q: How do I install the UBOS MCP Server? A: Installation involves creating a dedicated Conda environment, installing Jupyter components and the specific jupyter_collaboration version, handling pycrdt dependencies, enabling the collaboration extension, building the patched Docker image, and starting JupyterLab with a secure token.

Q: How do I configure the UBOS MCP Server? A: Configuration is done via environment variables passed through the MCP client configuration (e.g., claude_desktop_config.json). Key variables include SERVER_URL, TOKEN, NOTEBOOK_PATH, LOG_LEVEL, and OUTPUT_WAIT_DELAY.

Q: How do I use the UBOS MCP Server with Claude Desktop? A: Install Claude Desktop, locate claude_desktop_config.json, add/modify the mcpServers block with the appropriate Docker run command and environment variables, save the config file, and restart Claude Desktop.

Q: What tools are available in the UBOS MCP Server? A: Available tools include list_notebook_directory(), get_file_content(), set_target_notebook(), add_cell(), execute_cell(), delete_cell(), move_cell(), search_notebook_cells(), split_cell(), get_all_cells(), edit_cell_source(), get_kernel_variables(), get_all_outputs(), install_package(), and list_installed_packages().

Q: What is UBOS? A: UBOS is a full-stack AI Agent Development Platform focused on bringing AI Agents to every business department. It helps orchestrate AI Agents, connect them with enterprise data, build custom AI Agents with LLM models, and create Multi-Agent Systems.

Q: How does UBOS enhance the UBOS MCP Server? A: UBOS provides a seamless environment for integrating the MCP Server into AI Agent development workflows through centralized orchestration, data integration, custom AI Agent development, multi-agent systems support, and scalable infrastructure.